[ViewVC] Annotation of: cvs/cvsroot/AnyEvent-MCP/README

NAME
    AnyEvent::MCP::Intro - using MCP servers, clients and permissions

DESCRIPTION
    You can use the servers in this distribution without writing any Perl.
    This walkthrough starts with one filesystem server, connects it to an
    MCP client, and makes a useful request. Once that works, it explains
    persistent configuration, permissions and combining several servers.

    If you want to write a small server yourself, continue with "TUTORIAL"
    in AnyEvent::MCP::Server::Simple. Applications needing their own
    connection management or dispatch can use the modules described in
    "MODULES" in AnyEvent::MCP.

    The examples use "/home/alice/src/project" as an existing project
    directory. Replace it with your own absolute path. Commands shown here
    are commands for you to run; requests addressed to the LLM are shown
    separately.

INSTALLATION
    Install the Perl distribution and the external programs used by the
    servers. Installing one does not install the other.

    For mcp-fs, install Linux bubblewrap and the filesystem utilities. On
    Debian or Ubuntu, for example:

       sudo apt install bubblewrap findutils grep patch sed perl yad

    "yad" is optional: it supplies graphical permission dialogs. Without a
    usable YAD dialog, the helper tries "/dev/tty"; if neither is available,
    it denies the request. Bubblewrap's executable is "bwrap". The machine
    must allow the unprivileged user namespaces it needs.

    mcp-fs detects its utilities at startup and omits tools whose utilities
    are unavailable or unsuitable. It requires bubblewrap by default. See
    "TRUSTED CONFIGURATION" in mcp-fs for explicit utility paths and
    "LIMITATIONS" in mcp-fs for the sandbox's limits.

    If you have an unpacked distribution or source checkout, run these
    commands in its top-level directory:

       perl Makefile.PL
       make
       make test
       make install

    "perl Makefile.PL" reports missing Perl dependencies. Install those with
    your usual package manager or CPAN client before continuing. For
    example, the main non-core dependencies can be installed with:

       cpan AnyEvent AnyEvent::HTTP common::sense JSON::XS

    Use the same Perl installation for dependency installation, building and
    running the servers. A module installed for the system Perl might not be
    available to a Perl installed under "/opt". "make install" needs write
    access to the selected Perl's installation directories; use an
    appropriate local Perl installation or run that final step with the
    required privileges.

    Installation puts "mcp-fs", "mcp-multibroker", "mcp-vim",
    "mcp-webbrowser", "mcp-ask-user", "anyevent-mcp" and
    "anyevent-mcp-askpermission" in the selected executable directory. Make
    that directory available in the environment of your MCP client, or
    configure absolute executable paths. A desktop application need not have
    the same "PATH" as your shell.

    To try an uninstalled source tree after installing its dependencies, you
    can run a program with the source library path:

       perl -Ilib bin/mcp-fs --stdio --name code /home/alice/src/project

    Do this from the distribution directory. When configuring a client to
    start such a command, account for the client's working directory or use
    absolute paths to Perl, "lib" and the script. An installed executable
    avoids that extra setup.

CONNECTED BROWSER PAGES
    "mcp-webbrowser" is the browser-page counterpart to "mcp-vim". Its own
    HTTP/WebSocket listener remains active when MCP uses stdio or
    "--connect":

       mcp-webbrowser --stdio
       mcp-webbrowser --print-url

    A userscript or extension explicitly enables a page and connects to the
    WebSocket URL formed from the returned address. The broker supplies
    "pages" and asynchronous "execute" tools, page-name collision/reconnect
    handling, permission prompts, cancellation and execution timeouts. The
    browser client implements JavaScript evaluation and awaits Promise
    results. See "BROWSER PROTOCOL" in mcp-webbrowser for the small wire
    contract.

    The userscript/extension UI is a separate component and is not included
    yet. DOM revision tracking and acknowledgement-before-navigation remain
    client design work. To keep a lazily spawned multibroker child available
    for browser connections from startup, use "--eager":

       mcp-multibroker browser --- mcp-webbrowser --- --eager

YOUR FIRST FILESYSTEM SERVER
    Start with one project and one connection. You do not need a
    multibroker, a hand-written configuration file or saved permission rules
    yet.

  Choose stdio or HTTP
    Use stdio when your MCP client runs on the same machine and can launch a
    server process. Configure the client to start the following command:

       mcp-fs --stdio --name code /home/alice/src/project

    The client starts this process and uses its stdin/stdout for MCP. You do
    not start a second copy in a terminal, and there is no listener URL or
    HTTP token to configure. Diagnostics go to stderr.

    Clients that take a command and an argument array need these values:

       command: mcp-fs
       arguments: --stdio, --name, code, /home/alice/src/project

    These describe separate arguments, not one shell command string. Use an
    absolute executable path if the client cannot find "mcp-fs". See "CLIENT
    EXAMPLES" for examples of particular clients.

    Use HTTP when the client connects to an already-running server, or when
    it cannot launch a local process. Start this in a terminal on the server
    machine and leave it running:

       mcp-fs --name code --bind :31741 /home/alice/src/project

    In another terminal, obtain the matching connection URL:

       mcp-fs --name code --bind :31741 --print-url

    The second command prints a credential-bearing URL and exits without
    opening a listener. Configure that URL in the client. The default
    address is IPv4 loopback, so this example is reachable from the same
    machine only. A hosted client needs a suitable tunnel or reachable
    endpoint; its own "localhost" is not your computer.

    Repeat the same name and listener overrides when printing the URL. Both
    commands must use the same user and configuration directory. Port zero
    chooses an ephemeral port, which "--print-url" cannot predict; use an
    explicit port for this walkthrough.

    The HTTP server generates and saves its private master secret when
    needed. You can initialize it explicitly with "anyevent-mcp init", but
    that command is unnecessary when configuration already exists and will
    refuse to replace it. Keep the printed URL private: possession of its
    token authenticates a client.

  Make a useful request
    Once your client reports that the server is connected, ask the LLM:

       Show me the configured workdirs. List the top-level files in the
       project, then read its README. Do not modify files or run commands.

    "workdirs" returns the configured paths, sandbox grants, trusted mounts
    and runtime paths. Listing names requests "inspect" permission; reading
    contents requests "read" permission. Expect a permission prompt when
    there is no saved rule allowing the operation.

    Choose "Allow once" for the first operation. The worker then runs with
    the requested sandbox grants. A denial is a tool failure that the LLM
    should report, rather than an empty file or a disconnected server.

    For a slightly larger task, ask:

       Find TODO comments in this project and explain the three that look
       most useful to address next. Do not modify files or run commands.

    This can use "find", "grep" and "read-lines". You need not write MCP
    requests yourself. If a client offers its own tool-approval prompt, that
    is an additional client policy; it does not replace mcp-fs's
    permissions.

  Understand the workdir
    The directory passed at startup tells mcp-fs which workdir to expose. It
    does not grant permission for every operation in that directory. Each
    operation still requests its action and sandbox grants.

    With one workdir, tools can omit the "workdir" argument. With several:

       mcp-fs --stdio --name code /home/alice/src/project /home/alice/notes

    tools select one using a persistent positive integer ID, a numeric
    string or an exact configured/resolved path returned by "workdirs". The
    "workdirs" and "resolved_workdirs" objects use these IDs as keys.
    Relative tool paths are relative to that selection. Permission rules
    continue to use the configured path, not its numeric ID.

    IDs are shared across filesystem servers in
    "$XDG_CONFIG_HOME/anyevent-mcp/fs-workdir-ids.json", or under
    "$HOME/.config" by default. They identify resolved absolute paths and
    survive restarts and argument reordering. Startup resolves IDs once and
    reserves new allocations under the lock. A timer runs immediately and
    every 5.25 days to reread the registry and refresh the server's fixed
    assignments. Other entries expire after seven days and their IDs may be
    reused. Restart servers after manually changing the registry.

    "workdir-read" exposes the selected workdir read-only. "workdir-write"
    makes it writable and implies read access. A path in another configured
    workdir requires all-workdirs authority; a path elsewhere requires
    suitable home/world or shared-tmp authority. A symlink cannot make an
    unmounted target appear inside the sandbox.

    Prefer separate, non-overlapping workdirs. Overlapping mounts have
    unspecified access effects. See "SANDBOX GRANTS" in mcp-fs before
    granting access beyond the selected workdir.

  Inspect version-control changes
    For a Git, SVN, CVS or Mercurial working copy, ask the LLM to use
    "vcs-diff" and "vcs-status", with "backend" set to "git", "svn", "cvs"
    or "hg". "workdirs" reports the available clients. These tools accept
    filenames and construct the command themselves; no shell pipeline or
    arbitrary VCS options need to be approved.

    For example:

       Show the CVS diff for this project, limited to 200 lines.
       Then show its status, keeping stdout lines matching "File:|Status:".

    These operations have their own permission actions. They request read
    access to the selected workdir and home configuration; CVS also requests
    network access automatically. Read permission for ordinary file tools
    does not automatically authorize a VCS operation.

    For arbitrary "exec" commands, the same output options are available:
    "grep" filters stdout using PCRE, "max_lines" limits matching stdout
    lines, and "max_bytes" bounds returned bytes per stream. Prefer these
    options to a shell wrapper that mixes execution and output processing.
    Stderr is unfiltered, and exit status still describes the original
    command.

    Defaults return at most 2000 stdout lines and 64 KiB per stream. Raw
    capture has a separate 1 MiB limit per stream. A true
    "capture_truncated" means output was omitted before filtering or
    collection ended on timeout, so absent matches do not prove the omitted
    output had none. See "Command output" in mcp-fs for all result flags and
    limits.

CONFIGURING YOUR SETUP
    There are three different things to configure: how the client connects,
    how the server runs, and which operations the user allows. Changing one
    does not necessarily change the other two.

  Where each setting belongs
    Directories to expose
        Pass workdirs on the mcp-fs startup command. For a stdio server,
        that command belongs in the client's server configuration. For an
        HTTP server, it belongs in the command used to run the service.

    Connection transport
        The client launches a command for stdio or connects to a URL for
        HTTP. "--stdio" selects the former for mcp-fs and the multibroker.

    Listener address, port and tokens
        Use "[instance NAME]" in the global configuration or command-line
        "--bind" and "--token" overrides.

    Trusted mounts and utility paths
        For mcp-fs, use "[program NAME]" defaults and "[instance NAME]"
        overrides in the global configuration.

    Allowed operations and sandbox grants
        Use the permission rules file, normally created through approval
        dialogs. This file is separate from the global configuration.

    Location of permission prompts
        Use "--ask helper", "--ask tty", "--ask yad", "--ask auto" or "--ask
        mcp", or set "PERL_ANYEVENT_MCP_PERMISSION_ASK" in the server's
        environment.

    Combined server connections
        Put prefix/server pairs on the multibroker startup command. HTTP
        child credentials can also use "[client PREFIX]" in the global
        configuration.

  One complete named configuration
    The global file is "$XDG_CONFIG_HOME/anyevent-mcp/global.ini", falling
    back to "$HOME/.config/anyevent-mcp/global.ini". Settings are UTF-8 "key
    = value" lines; values are unquoted. Whole-line "#" and ";" comments are
    allowed. See "GLOBAL CONFIGURATION" in AnyEvent::MCP for the complete
    format.

    Start with the existing file, preserving its "[global]" secret. If you
    have no file yet, "anyevent-mcp init" creates it privately. Add the
    following sections:

       [program mcp-fs]
       mount.opt = ro:/opt

       [instance code]
       bind = 127.0.0.1:31741

    The optional "mount.opt" line assumes "/opt" exists and contains tools
    or libraries your workers need. Omit it if you do not need that access.
    The ordinary sandbox runtime includes "/usr", "/bin" and system
    libraries, but not "/opt". If your worker Perl is "/opt/bin/perl", you
    can additionally put "executable.perl = /opt/bin/perl" in that program
    section. Supply the actual executable path; selecting it does not itself
    mount its files or libraries.

    Now start:

       mcp-fs --name code /home/alice/src/project

    and retrieve its URL with:

       mcp-fs --name code --print-url

    Both use "[instance code]". No explicit token is needed: the server
    derives one from its name and the existing master secret.

    For this setup:

       program defaults: [program mcp-fs]
       instance settings: [instance code]
       selected workdir: /home/alice/src/project
       permission file: ~/.config/anyevent-mcp/rules/fs-code.ini
       rule-manager profile: fs-code

    The permission pathname above assumes the default configuration
    directory. "anyevent-mcp manage-rules fs-code" opens the graphical rule
    manager; "anyevent-mcp edit-rules fs-code" opens the file in your
    editor.

    Keep global configuration and rule files owned by the server user and
    private, normally mode 0600. "--config FILE" on "anyevent-mcp init"
    selects that command's output file; it does not make the servers use an
    arbitrary alternate file. Use the same "HOME"/"XDG_CONFIG_HOME"
    environment when running the server and its management commands.

  Names, prefixes and profiles
    "--name code" selects instance settings, derived HTTP credentials and
    mcp-fs's "rules/fs-code.ini". Without "--name", mcp-fs uses "default",
    giving profile "fs-default". Two processes with the same program, name
    and configuration share credentials and rules, even if their workdirs
    differ.

    A multibroker prefix, such as "files", only routes tools: "grep" becomes
    "files.grep". It does not rename the child server or select its rules.
    For example:

       mcp-multibroker files \
          'stdio:mcp-fs --name code /home/alice/src/project'

    The tools are "files.*", but the child still uses instance "code" and
    rule-manager profile "fs-code". The multibroker's own "--name" selects
    its upstream listener settings.

  Configuration changes and restarts
    Command-line listener options override the named global settings. For
    mcp-fs trusted settings, an instance entry overrides the corresponding
    program entry; an empty instance mount value suppresses the inherited
    mount.

    Workdirs, mounts, utility paths, listener settings and tokens are read
    at startup. Change the file or startup command, then restart the
    affected server. The multibroker also needs restarting to change its
    prefix/server pairs; refreshing discovery does not change those pairs.

    Permission rules are reread on permission checks, so editing them does
    not require a restart. A client's displayed tool list can still be
    cached. After restarting a child, refresh tool discovery or reconnect
    the client as described in "COMBINING SERVERS".

PERMISSIONS IN PRACTICE
    HTTP authentication establishes that the client may connect. Permission
    checks decide whether a tool may perform an operation. A correct token
    therefore does not prevent permission prompts.

  What the prompt means
    The prompt describes an action, paths or command, a reason and sandbox
    grants. For filesystem tools, the actions are:

       inspect     stat, list, find
       read        file-read, read-lines, grep
       write       file-write, file-patch
       manage      path-op
       exec        arbitrary command execution
       vcs-diff    working-copy differences
       vcs-status  working-copy status

    The action and grants are independent. Allowing "read" does not allow
    "write", even if a worker grant permits both kinds of filesystem access.
    "exec" runs arbitrary commands; it is not a classification of supposedly
    safe command prefixes.

    Choose allow/deny once, or always. Closing the dialog denies once. An
    optional denial reason is returned with the error; it is not added to
    successful tool results. An always choice opens a rule editor. Choose an
    indefinite lifetime (the default), 900 seconds or 16 hours. Finite
    lifetimes are stored as "expires" Unix timestamps. Expired rules
    disappear on every read; the next ordinary save removes them from disk.
    Expiry affects future permission checks, not operations already
    authorized. Filesystem allow rules can select grants and the selected
    workdir when the authority depends on it. Deny rules can also select an
    exact affected path. Exec offers persistent command/argv subjects.

    For exec, "View stdin..." lets you inspect supplied input without
    closing the approval dialog. Filesystem and Vim patch tools similarly
    offer "View patch...", including the target file or editor and buffer.
    Longer text is shown as an explicitly incomplete preview. These are YAD
    button labels; other interfaces can show the details inline. That input
    is display-only: an exec allow rule does not constrain future stdin.
    Allowing an interpreter command can therefore allow a different script
    on its next invocation.

    A worker accessing several paths requests their combined sandbox
    authority once. If the chosen grants are insufficient, it fails before
    starting.

  Save a useful read-only policy
    After trying individual operations, you might want the LLM to inspect
    and read the project without asking each time, while keeping changes
    subject to approval. Put these rules in "rules/fs-code.ini", or create
    equivalent allow rules through the prompt:

       [rule]
       decision=allow
       action=inspect
       workdir=/home/alice/src/project
       sandbox-grants=workdir-read

       [rule]
       decision=allow
       action=read
       workdir=/home/alice/src/project
       sandbox-grants=workdir-read

       [rule]
       decision=deny
       action=exec

    Use the exact workdir spelling passed at server startup. Absolute
    startup paths make this easier. If creating the rules file manually,
    ensure it belongs to the server user and is private before making
    another request. For the default configuration directory:

       chmod 600 ~/.config/anyevent-mcp/rules/fs-code.ini

    Use the corresponding XDG path when configured. Without matching rules,
    write and manage operations still ask. The final rule denies command
    execution outright; omit it if you want execution to ask instead.

    Rules run in order, stopping at the first match. An allow rule matches
    only when its grants cover the request, including implications.
    "workdir-write" implies "workdir-read"; "network" remains independent.
    Action and subject match exactly unless beginning with "^", which
    selects a Perl regular expression. Workdir matching is always exact. An
    explicit "ask" rule can override later allow rules.

    These allow rules authorize sandbox access to the selected workdir. They
    cannot confine authority to one file or a subtree inside it. Filesystem
    operations do not offer persistent path subjects. An exact "path"
    matcher is available for deny rules only. Trusted runtime and configured
    mounts remain baseline access independently of these grants. See
    "TRUSTED CONFIGURATION" in mcp-fs.

  Change or remove saved rules
    Use:

       anyevent-mcp manage-rules fs-code
       anyevent-mcp edit-rules fs-code

    The first command lets you delete and reorder rules in YAD. The second
    uses $VISUAL, $EDITOR, "sensible-editor" or "vi". An earlier deny or ask
    rule can explain why adding a later allow rule does not change the
    result.

    For a custom application with another rule pathname, use:

       anyevent-mcp manage-rules-file /path/to/rules.ini
       anyevent-mcp edit-rules-file /path/to/rules.ini

    A failed attempt to save a permanent rule is an error, not a successful
    permanent approval. The file must remain private and owned by the server
    user. For full syntax and programming interfaces, see
    AnyEvent::MCP::Server::Permissions.

  Choose where to ask
    The default "helper" mode runs "anyevent-mcp-askpermission" on the
    server machine. It tries YAD, then "/dev/tty", then denies if neither
    can be used. The helper inherits the server's display environment.
    "--ask tty" and "--ask yad" instead force the built-in terminal or YAD
    interface. They ignore custom helper settings and never try another
    interface. These modes work for permission prompts and ordinary forms,
    including forms handled by a multibroker.
    "PERL_ANYEVENT_MCP_PERMISSION_HELPER" selects a different executable.

    For a modern client supporting MCP form elicitation, you can instead
    use:

       mcp-fs --stdio --name code --ask auto /home/alice/src/project

    "auto" uses the client's form support when advertised for that request,
    otherwise the local helper. "mcp" requires that support and fails when
    unavailable. It does not silently fall back. Use client-side permission
    approval only when that client is a trusted authority to grant access.

    To set the default for servers using the shared permission engine:

       PERL_ANYEVENT_MCP_PERMISSION_ASK=auto \
          mcp-fs --stdio --name code /home/alice/src/project

    An explicit application "ask" setting or "--ask" overrides the
    environment. For spawned stdio children, "mcp-multibroker --ask auto"
    passes this default to them. It cannot change the environment of an
    independently running HTTP server.

    The multibroker can handle form elicitation locally for both stdio and
    HTTP children. "--ask helper" selects local dialogs even if the upstream
    client advertises native forms; "--ask mcp" forwards forms upstream, and
    "auto" uses native forms when advertised. If a client claims support but
    silently declines questions, use "helper". A decline never causes a
    fallback prompt.

    Standalone "mcp-ask-user" also supports these modes and defaults to the
    local helper. A question is different from an approval: answering it
    does not grant a filesystem worker any authority.

COMBINING SERVERS
    Once the first connection works, use the multibroker to give a client
    one connection for several servers:

       mcp-multibroker --name tools --bind :31740 \
          code 'stdio:mcp-fs --name code /home/alice/src/project' \
          notes 'stdio:mcp-fs --name notes /home/alice/notes'

    Quote each "stdio:" shell command as one argument. The broker supplies
    the child's stdio environment and starts ordinary children lazily, on
    first use. The explicit child names give them separate permission
    profiles "fs-code" and "fs-notes".

    Obtain the upstream HTTP URL with:

       mcp-multibroker --name tools --bind :31740 --print-url

    Configure this URL in place of the client's old direct connection. The
    client can now see "code.grep", "code.read-lines", "notes.find" and
    other prefixed tools. It does not need a separate connection to each
    child.

    For a client launching the multibroker locally, configure:

       mcp-multibroker --stdio --name tools \
          code 'stdio:mcp-fs --name code /home/alice/src/project' \
          notes 'stdio:mcp-fs --name notes /home/alice/notes'

    "--stdio" selects the upstream connection. The child commands still use
    "stdio:"; that selects each downstream connection independently. No
    upstream HTTP URL is needed in this case.

  Discover and refresh tools
    Ask the LLM:

       Call discover-brokers and list-tools, then show me which servers
       are available and what each is for.

    "discover-brokers" returns instructions, no instructions, or an error
    for each configured server. "list-tools" requests current tool
    definitions; unreachable servers are omitted. A reachable server can
    still fail later.

    If the client still has an old direct tool list, "call-tool" can invoke
    an exact prefixed name found by "list-tools". Refresh the client's MCP
    connection if it continues to hide newly available tools.

    Discovery queries configured servers and currently registered reverse
    connections. Changing the static downstream command still requires a
    restart.

  Let a server connect to the multibroker
    To add independently started servers without editing the multibroker
    command, keep its HTTP/extension listener active alongside stdio:

       mcp-multibroker --stdio --listen --bind 127.0.0.1:31740
       mcp-multibroker --bind 127.0.0.1:31740 --print-url

    Append an alias to the returned credential-bearing URL:

       mcp-fs --connect http://127.0.0.1:31740/TOKEN/files /home/alice/project

    The filesystem server initiates the TCP connection but remains the MCP
    server. The multibroker authenticates the same token used for HTTP,
    registers the alias and discovers the tools. A configured or connected
    alias cannot be replaced. After disconnecting, the server retries once
    per second for sixty attempts. Pending calls fail and are never
    replayed. Remote registration does not grant the multibroker
    spawned-child shutdown authority.

    The hello is a raw JSON line, followed by ordinary MCP JSONL on the same
    socket; the HTTP-shaped URL is an address and credential, not an HTTP
    request. The bundled connector supports plain "http://" endpoints. An
    HTTP listener is already active by default when the upstream connection
    is HTTP.

  Add an HTTP child
    A broker can mix spawned stdio servers and existing HTTP endpoints:

       mcp-multibroker --stdio \
          code 'stdio:mcp-fs --name code /home/alice/src/project' \
          remote https://example.org/mcp/ --bearer TOKEN

    "--bearer" immediately after the HTTP pair belongs to that child.
    "--token" before all pairs configures the multibroker's own HTTP
    listener. They authenticate different connections.

    To avoid putting a child's bearer token in the startup command, add:

       [client remote]
       bearer = TOKEN
       timeout = 300

    to the private global configuration, and omit "--bearer" from the
    command. The prefix "remote" selects these client defaults. The
    command-line URL still chooses the endpoint. Use the actual credential
    accepted by that server, not the literal placeholder "TOKEN".

    A token already present in a child's URL needs no separate bearer
    option. The bundled servers use static URL-safe tokens; they do not
    validate OAuth access tokens or implement HTTP Basic authentication. Use
    TLS or an appropriate tunnel when credentials cross untrusted networks.

    The multibroker does not put every child inside the mcp-fs sandbox. Each
    process or remote service has its own authority and enforcement.

  Add a live Vim editor
    Install the Vim plugin using "VIM PLUGIN INSTALLATION" in mcp-vim. It is
    included in the source distribution but is not installed by Perl's "make
    install".

    A spawned mcp-vim child also listens for editor connections. Start it
    eagerly so Vim can connect before the first MCP tool call:

       mcp-multibroker --stdio \
          code 'stdio:mcp-fs --name code /home/alice/src/project' \
          vim 'stdio:mcp-vim --name editor' --eager

    In another terminal, obtain the editor child's URL prefix:

       mcp-vim --name editor --print-url

    Append the desired target name in Vim:

       :Mcp http://HOST:PORT/TOKEN/my-editor

    Use the actual printed prefix in place of "http://HOST:PORT/TOKEN/". Ask
    the LLM to call "vim.targets", then "vim.state" before reading or
    editing buffers. These tools see live, possibly unsaved buffers. Edits
    require a current changedtick and do not save files to disk.

    To pass arguments directly, use "PREFIX --- PROGRAM ARG... ---":

       mcp-multibroker --stdio \
          vim --- mcp-vim --name editor --bind :: --- --eager \
          code --- mcp-fs --name code '/home/alice/project with spaces' ---

    Only the invoking shell processes quoting. The broker passes all
    arguments between the delimiters unchanged, including empty arguments
    and child options. Use "stdio:COMMAND" for shell syntax or a literal
    "---" child argument. An empty command or missing closing delimiter is
    an error.

    "--eager" belongs immediately after its stdio URL or closing "---". An
    eager connection failure is logged; the broker does not continuously
    restart the child. Later tool use can try connecting again.

  Ask the client's human a question
    To let the assistant ask you questions, add a question server:

       mcp-multibroker --stdio \
          code 'stdio:mcp-fs --name code /home/alice/src/project' \
          questions 'stdio:mcp-ask-user'

    The LLM can call "questions.ask-user" with a question, up to three
    suggested answers and room for free text. For example, tell it to use
    that tool if choosing among several possible tasks needs your input. For
    several fields or other value types, "questions.ask-form" accepts
    "message" and "requestedSchema" directly and returns the standard
    elicitation response. Both tools use the same configured presentation
    mode. Decline and cancel are distinct results; neither supplies an
    answer.

    By default the multibroker displays questions locally, using YAD or a
    terminal. Add "--ask mcp" before the broker entries to use the client's
    native forms, or "--ask auto" to select by advertised capability. This
    also works with "mcp-ask-user" started separately: give that server
    "--ask mcp" so it delegates presentation to its connecting multibroker.

    "anyevent-mcp-form-elicitation" is the standalone form renderer. It
    reads standard MCP form parameters as UTF-8 JSON on stdin and writes an
    accept/decline/cancel response as JSON on stdout.
    "PERL_ANYEVENT_MCP_ELICITATION_HELPER" selects a replacement executable.
    See anyevent-mcp-form-elicitation for supported fields and mcp-ask-user
    for question arguments and result fields.

HTTP TOKENS AND SERVER IDENTITY
    For the ordinary bundled HTTP endpoints, a client can present an
    accepted token in either of these ways:

       POST /TOKEN/
       POST /                 Authorization: Bearer TOKEN

    URL tokens are path components, not browser cookies. For another
    configured endpoint, "/TOKEN" prefixes that endpoint path. All accepted
    tokens authenticate the same operations; they are not separate users or
    permission levels. Permissions still govern the tool operation.

    By default, the master secret and server name determine one stable token
    and a port in 16384..32767. Changing a server's name changes its derived
    credentials and default port. Changing or losing the master secret
    changes all derived credentials. Keep an existing "[global]" secret when
    editing other configuration.

    To configure explicit tokens:

       [instance code]
       tokens = first-secret,second-secret

    Replace those placeholders with actual unguessable URL-safe tokens.
    Repeated "--token" options replace the whole configured list and the
    derived default. The first token appears in "--print-url"; all are
    accepted. mcp-vim also accepts its token set for Vim and browser
    WebSocket connections.

    If "--print-url" disagrees with the client's URL, compare the name,
    command-line overrides, user and configuration environment with the
    running process. The command resolves configuration; it does not ask the
    running server which URL it uses. A changed file needs a server restart.

    An Origin allowlist restricts browser origins; it does not authenticate
    clients. A CORS preflight can succeed without a token, while the MCP
    POST still requires one. See "AUTHENTICATION" in
    AnyEvent::MCP::Server::HTTP for the low-level server interface.

CLIENT EXAMPLES
    Client settings and command syntax evolve independently of this
    distribution. These examples show the connection choices; consult the
    linked client documentation if its interface differs. Replace
    illustrative paths and credentials with your own.

  OpenAI Codex CLI
    For the first direct filesystem connection:

       codex mcp add code -- \
          mcp-fs --stdio --name code /home/alice/src/project
       codex mcp list

    For a multibroker connection:

       codex mcp add mytools -- \
          mcp-multibroker --stdio \
          code 'stdio:mcp-fs --name code /home/alice/src/project'

    Use "/mcp" within Codex to inspect connections. See Codex MCP
    documentation <https://learn.chatgpt.com/docs/extend/mcp>.

  Anthropic Claude Code
    For the direct connection:

       claude mcp add --transport stdio --scope user code -- \
          mcp-fs --stdio --name code /home/alice/src/project
       claude mcp list

    Replace the launched command with the multibroker command above when you
    want several servers. Use "/mcp" for connection status. See Claude Code
    MCP documentation <https://code.claude.com/docs/en/mcp>.

  Google Gemini CLI
    Merge a direct server entry into "~/.gemini/settings.json":

       {
         "mcpServers": {
           "code": {
             "command": "mcp-fs",
             "args": [
               "--stdio", "--name", "code", "/home/alice/src/project"
             ]
           }
         }
       }

    For a combined connection, use "mcp-multibroker" as the command and its
    "--stdio" and prefix/server pairs as the argument array. Use "/mcp" to
    inspect the connection. See Gemini CLI MCP documentation
    <https://geminicli.com/docs/tools/mcp-server/>.

  Hosted clients, including ChatGPT web
    A hosted client cannot spawn your local stdio command or reach your
    machine's loopback address directly. Run the server or multibroker in
    HTTP mode and configure a supported tunnel or reachable endpoint.

    For ChatGPT, use its custom MCP setup and, for a private server, an
    appropriately configured Secure MCP Tunnel. Availability depends on the
    client's plan, workspace and feature permissions. See ChatGPT custom MCP
    servers
    <https://developers.openai.com/api/docs/guides/custom-mcp-server> and
    Secure MCP Tunnel
    <https://developers.openai.com/blog/connect-private-mcp-servers-to-opena
    i-products>.

TROUBLESHOOTING
  The server does not start
    Read stderr or the client's server log. Missing Perl modules, a missing
    workdir, unsuitable utilities or an unavailable bubblewrap executable
    can fail startup. Confirm that the client launches the same executable
    and arguments you intended, with the expected "PATH" and Perl
    installation.

    For a local sandbox check, run from the project directory:

       mcp-fs --exec-cmd workdir-read -- ls

    This runs "ls" with the named grants and trusted baseline mounts,
    without MCP or saved permission rules. A failure here can identify a
    bubblewrap or runtime problem. It does not test the client connection or
    approval UI. "--sandbox none" disables isolation and changes worker
    authority; it is not a fix that preserves the same permission boundary.

  The client cannot connect
    For stdio, configure a command the client launches, rather than a URL. A
    separately running stdio process is not the client's connection. Do not
    put banners or diagnostics on stdout.

    For HTTP, leave the server running and check its address and port.
    "--print-url" exits without starting it. Loopback binds accept local
    connections only; hosted or remote clients need the appropriate route or
    tunnel. An occupied port causes a listener error, so check the server
    log.

  Authentication fails
    Obtain the URL with the same name, bind/token overrides and
    configuration environment as the running process. Use the complete path,
    including any required trailing slash. A clean URL needs an accepted
    bearer token.

    A multibroker child credential is not necessarily the upstream
    listener's credential. "--bearer" after a child pair and "--token"
    before the pairs configure different sides of the connection.

    If the server warns that it cannot save the master secret, another
    process may derive a different token. Fix ownership and write access to
    the private configuration. Do not replace an existing secret simply to
    add a setting.

  Connected, but there are no tools
    Inspect the server's stderr for omitted utilities. mcp-fs's "workdirs"
    tool reports configuration even when a utility-dependent tool is absent.
    For a multibroker, call "discover-brokers" to see individual connection
    errors, then "list-tools" to refresh definitions.

    A third-party child might require initialization or features this client
    implementation does not support. See AnyEvent::MCP::Client and its
    transport documentation for limitations.

  There is no approval dialog
    First check whether the tool was denied by a saved rule or is waiting
    for the client's own approval. An allowed operation needs no server
    prompt.

    The default helper runs on the server machine. A background service may
    have neither a usable display nor "/dev/tty", even though your
    interactive shell has both. Supply the appropriate display environment,
    a usable helper, or "--ask auto" with a modern client supporting form
    elicitation. "--ask mcp" reports an error if that support is absent.

    Setting an asking mode cannot make an unsupported client display a form.
    Check stderr and the tool error instead of assuming a missing dialog is
    an approval.

  It asks again after I chose allow
    Allow-once covers one tool invocation, including its permission retries.
    The next invocation asks again. Use allow-always to save a rule.

    Inspect the saved rule's action, workdir and grants. Listing names and
    reading contents are different actions. A rule for one exact workdir
    spelling will not match a differently spelled startup argument. A
    request for extra authority, such as networking, does not match a
    workdir-read-only allow rule. Earlier ask or deny rules take precedence.

    Confirm that the prompt's permanent rule was successfully saved and that
    you are editing the rules for the actual child name, not merely its
    multibroker prefix.

  The worker cannot see a directory or executable
    The worker sees granted mounts and trusted baseline mounts, not
    everything the server process can see. Check "workdirs" for the selected
    path, mounts and runtime paths. A symlink target outside those mounts is
    unavailable.

    For tools or libraries under "/opt", add an appropriate trusted mount as
    shown earlier and restart mcp-fs. A configured executable path alone
    does not mount the executable or its dependencies inside the worker. A
    trusted mount supplies baseline access to every worker using it; a
    writable mount likewise supplies baseline write authority.

    An arbitrary command might also need its user's configuration or
    repository credentials under HOME, or network access. Request the
    corresponding grants when needed; do not assume "workdir-read" includes
    them. For example, CVS over SSH can use "workdir-read" and "ssh-agent".
    The latter includes network access, the agent socket and
    "~/.ssh/known_hosts", without exposing private key files or the rest of
    HOME. The broker must inherit "SSH_AUTH_SOCK" from your environment.
    User-configured helpers outside the runtime mounts need an explicit
    trusted mount. An explicit exec grant array replaces the default rather
    than adding to it.

  My configuration change seems to be ignored
    Check which file and section the process actually selects. Global
    settings use the server user's "HOME"/"XDG_CONFIG_HOME". Instance names,
    program basenames and multibroker prefixes serve different purposes.

    Restart after changing startup settings, mounts or utilities. Permission
    rules need no restart, but their order still matters. Refresh discovery
    after a child restart; reconnect a client that retains an old tool list.
    "--print-url" reads the current configuration, which can differ from an
    older running process.

  The command failed, but the MCP request succeeded
    "exec" reports exit status, signal or timeout as a normal tool result. A
    successful MCP exchange is not a successful Unix command. Conversely, a
    transport failure does not prove a command did nothing: it may have
    completed before the connection was lost. Calls are not automatically
    replayed after a transport failure.

TESTING
    The default test level is 0. It checks protocol behaviour, permissions,
    validation and ordinary process operation, including worker cancellation
    and reaping. Watchdogs allow slow machines time to finish; they do not
    make successful tests wait for the whole timeout.

       prove -Ilib t

    Set "PERL_ANYEVENT_MCP_TESTS" to 1 to include the extended tests:

       PERL_ANYEVENT_MCP_TESTS=1 prove -Ilib t

    Level 1 adds GNU find/grep/sed/patch operations, real Vim scripting,
    browser transfer integration, short idle-lifetime tests, a helper
    descendant holding a pipe open, and tests which deliberately wait for a
    command timeout or cancel a form helper across several processes. Run
    this level before releases. Values greater than 1 currently select the
    same tests as level 1.

    Missing GNU utilities or required Vim functions cause explicit skips
    even at level 1. The permission and form UI tests use a YAD stand-in:
    neither level requires YAD, X11 or an interactive display. The
    filesystem tests use a bubblewrap stand-in and check arguments and
    worker behaviour; they do not test kernel isolation. The browser tests
    use simulated peers.

WHERE TO GO NEXT
    For available tools and server-specific options:

       perldoc mcp-fs
       perldoc mcp-multibroker
       perldoc mcp-vim
       perldoc mcp-ask-user
       perldoc anyevent-mcp

    For a complete first Perl server, options, replies, permission checks
    and asynchronous work, see "TUTORIAL" in AnyEvent::MCP::Server::Simple.
    For the module map and shared configuration reference, see
    AnyEvent::MCP. For permission rule details, see
    AnyEvent::MCP::Server::Permissions.

SEE ALSO
    AnyEvent::MCP, AnyEvent::MCP::Server::Simple, mcp-fs, mcp-multibroker,
    mcp-vim, mcp-ask-user, AnyEvent::MCP::Server::Permissions

Revision:	1.2
Committed:	Fri Oct 16 15:35:14 2026 UTC (4 days, 9 hours ago) by root
Branch:	MAIN
CVS Tags:	HEAD
Changes since 1.1:	+971 -0 lines
Log Message:	* empty log message *