lib/AnyEvent/MCP.pm

=head1 NAME

AnyEvent::MCP - Model Context Protocol client/server support

=head1 SYNOPSIS

   use AnyEvent::MCP::Server::Simple ();

   mcp_tool ...
   mcp_start;

or use the object interface directly:

   use AnyEvent::MCP::Server ();

   my $server = AnyEvent::MCP::Server->new (...);

=head1 DESCRIPTION

AnyEvent::MCP provides event-driven Model Context Protocol client and server
support.

The usual way to implement a small MCP server is
L<AnyEvent::MCP::Server::Simple>, which provides a function-based interface and
creates the underlying server objects when a transport such as stdio or HTTP is
started.

The lower-level object interfaces are intended for applications that need to
manage MCP connections, servers or reusable tool registries directly.

=head2 MODULES

=over 4

=item L<AnyEvent::MCP::Server::Simple>

Function-based interface for implementing ordinary MCP servers.

=item L<AnyEvent::MCP::Server>

Object-oriented MCP server interface.

=item L<AnyEvent::MCP::Client>

Object-oriented MCP client interface.

=item L<AnyEvent::MCP::Server::Toolset>

Reusable registry of MCP tool declarations.

=item L<AnyEvent::MCP::Server::Permissions>

Permission and capability handling for MCP servers.

=back

C<mcp-multibroker> combines downstream HTTP and stdio servers under tool-name
prefixes. It uses the same client, server and permission helper facilities,
including modern input forwarding and local permission prompts for legacy
callers. Run C<mcp-multibroker --help> for command-line syntax; its manual
describes authentication and configuration.

The interfaces are still being designed; this documentation is intentionally
only an overview for now.

=head1 GLOBAL CONFIGURATION

The shared per-user configuration is C<$XDG_CONFIG_HOME/anyevent-mcp/global.ini>,
or C<$HOME/.config/anyevent-mcp/global.ini> when XDG_CONFIG_HOME is unset.
L<AnyEvent::MCP::Config> loads and holds it; loading this module does not access
configuration files.

The file is UTF-8 and uses sections with single-line C<key = value> pairs.
Values are unquoted strings. Blank lines and whole-line comments beginning
with C<#> or C<;> are ignored; inline comment characters remain part of the
value. Later occurrences of a key replace earlier ones in the same section.

   [global]
   secret = ...128 hexadecimal digits...

   [server example]
   port = 31740
   url = https://example.net:31740/{cookie}/

   [mcp-fs]
   utility = /path/to/utility

Section names are unrestricted. Application-specific sections, including
exports, utility paths and user settings, are documented by their applications.

C<[global]> holds C<secret>, a 64-byte master key encoded as 128 hexadecimal
digits. The file must be owned by the current user, with no group or other
permissions. A missing secret is generated automatically on first configuration
access and saved when possible. Existing secrets are never replaced implicitly.
An invalid secret is an error.

If saving fails, Config warns and retains the secret in memory. Credentials
then remain stable only for that process; other processes cannot derive the
same credentials. If randomness is unavailable, supply a securely generated
secret in the file.

C<[server NAME]> holds named-server settings. Its C<url> is a complete template;
C<{cookie}> is replaced with the cookie derived for that server and optional
username. Scheme, host, port and cookie placement are explicit in the template.
HTTP servers with an explicit C<name> load C<host>, C<port>, C<path>,
C<url_host>, C<url_scheme>, C<cookie>, C<bearer> and C<users> from this section
as defaults. C<users> is a comma-separated allowlist whose Basic passwords
are derived for the named server. An explicit password hash can instead be
passed to the constructor. C<url> is a template for the utility program; it
does not set the listener's address.

C<mcp_start> chooses an application name and supplies cookie/bearer
authentication by default. Explicit authentication settings replace this
default. Stdio startup does not access global configuration.

C<[client NAME]> supplies HTTP client defaults: C<url>, C<bearer>, C<username>,
C<password> and C<timeout>. Clients consult it only when explicitly given a
C<name>. An unnamed client or HTTP server does not read global configuration.
Explicit constructor arguments take precedence over named defaults.

=head1 ENVIRONMENT

Project-specific environment variables use the C<PERL_ANYEVENT_MCP_> prefix.
C<PERL_ANYEVENT_MCP_MULTIBROKER_PROTOCOL=stdio> selects stdio in Simple.
C<PERL_ANYEVENT_MCP_MULTIBROKER_ALIAS> supplies the default application name.
C<PERL_ANYEVENT_MCP_PERMISSION_HELPER> selects the external asking executable.
Standard C<HOME> and C<XDG_CONFIG_HOME> keep their standard names.

=head1 FUNCTIONS

=over

=item $bytes = AnyEvent::MCP::random_bytes $length

Returns exactly C<$length> random bytes. Tries C</dev/urandom>, then an external
C<openssl rand> command. No additional random-number module is required.
Dies if neither source supplies the requested bytes successfully.
C<$length> must be a nonnegative integer; zero returns an empty string.

=back

=head2 PATCH UTILITIES

Since applying patches to files is a common taks for MCP servers, the
following utility functions can be used to ease that job. Together, they
define a ocmmon patch format (unified diff or a simplified version of it,
with fewer requirements to make mto easier for the LLM to generate), helpers
to apply the patch and a helper to verify if the patch was applied
with sufficient precision.

The workflow would be:

=over

=item 1. AnyEvent::MCP::normalize_udiff

Retursn a unified diff for GNU patch, and meta data to verify its application.

=item 2. AnyEvent::MCP::apply_udiff

This should capture GNU patch output.

=back

If you apply the patch yourself, you should capture patch otuput, parse it
via C<parse_patch_output> and check limits via C<check_patch_output>.

=head3 Input format

The patch format accepted by normalize_udiff is an extension to the
(essentially undocumented) unified diff format.

In a hunk header, only the old start C<-N> matters. It is the old-file line
of the first hunk body line, including context, not necessarily the first
changed line. Counts and the new-file position are ignored and recomputed.
Both ordinary headers and the abbreviated form are accepted:

   @@ -42,99 +123,99 @@
   @@ -42 @@

Optional text after the closing C<@@> is preserved. File headers and other
text before the first hunk are preserved; a diff must describe one file.

Hunk body lines use the usual prefixes: a space for unchanged context,
C<-> for removed lines and C<+> for added lines. The
C<\ No newline at end of file> marker is preserved and counts neither side.
Trailing empty lines outside the final hunk are discarded.

Pure insertion is permitted only at the beginning, using old start zero.
An insertion elsewhere needs old-side context. Empty hunks are rejected.
New positions include the cumulative line-count changes of preceding hunks.

=head3 Applying the result

The C<normalize_udiff> function does not apply the patch, check file
contents or guard against concurrent edits. The caller must supply those
checks, if required.

Context must match exactly: apply with fuzz zero. For each hunk,
C<$max_offset> permits relocation by at most the number of distinct old-side
lines minus one, or zero for a pure insertion. Repeated old-side lines do
not increase this allowance. The applier must enforce these limits; an
unrestricted search for matching context can select the wrong occurrence.

For live Vim buffers, also require the expected changedtick to match.
File-based users need an equivalent check before replacing the file.

To work around GNU patch's handling of asymmetric context, the
first context line of each hunk is rewritten as an identity
removal/addition. The line contents and old/new line counts are
unchanged. This is normalization for the patch applier, not a relaxation
of context matching.

=over

=item ($diff, $max_offset) = AnyEvent::MCP::normalize_udiff $diff

Normalizes a relaxed, single-file unified diff into ordinary unified diff
syntax. Returns the normalized C<$diff> and an array reference C<$max_offset>
containing the permitted whole-hunk relocation for each hunk, in order.
Dies on malformed hunks or when no hunks are found.

Here is a suitable description for the diff format, e.g. in a tool
definition:

   Apply a unified diff to one regular file. Hunk counts are recomputed,
   fuzz is disabled, whole-hunk relocation is limited per hunk by distinct
   old-side lines. Pure insertion is allowed only at the beginning;
   elsewhere include old-side context.

=item $cv = AnyEvent::MCP::apply_udiff $input, $output, $diff

Asynchronously applies the relaxed C<$diff> to the input file C<$input>,
writing a separate output file C<$output>. C<$diff> must contain bytes;
callers working with characters must encode them for the file themselves.

Normalizes the diff, runs GNU patch using C<AnyEvent::Util::run_cmd>, and
validates its verbose output with C<check_patch_output>. The command uses
batch/forward mode, binary mode and fuzz zero. No shell is involved.

C<$output> must not exist. It is reserved with mode 0600; patch runs in its
directory so incidental temporary files stay there. Input and output paths
are made absolute before starting the command. These must be trusted paths
in a directory controlled by the caller.

Returns a condition variable. Its C<recv> returns the validated hunk array
reference, or throws on command/application failure. Setup failures throw
synchronously. Failed or partial output is removed. C<$input> is unchanged.

The caller owns committing the successful output and removing it when no
longer needed. Freshness checks, metadata preservation, atomic replacement
and application-specific permissions also belong to the caller.

For your reference, the exact options used are:

   --verbose --batch --forward --binary --fuzz=0
   --no-backup-if-mismatch
   --reject-file=- --output=... -- <inputfile>

=item $parsed = AnyEvent::MCP::parse_patch_output $output

Parses C<LC_ALL=C> GNU patch C<--verbose> output without judging whether
the application is acceptable. C<$parsed> has two fields:

=over

=item hunks => [$hunk...]

Hunk records in output order. Each record contains C<hunk> (the one-based
number), C<success>, C<line> (the reported application line), C<fuzz> and
the signed C<offset>. Omitted fuzz and offset are zero. Failed and ignored
hunks have false C<success>.

=item unparsed => [$line...]

Lines not recognized as hunk results or GNU patch's verbose framing.
The parser preserves them for callers to interpret or reject.

=back

Use verbose output: ordinary patch output omits exact-position successes,
so it cannot account for every hunk.

=item $hunks = AnyEvent::MCP::check_patch_output $status, $output, [$max_offset...]

Parses C<$output> and validates a complete application. C<$status> is the
raw process wait status, as returned by C<waitpid> or
C<AnyEvent::Util::run_cmd>, not just the exit code.

Requires status zero, no unrecognized output, exactly the expected hunks
in numbered order, successful application, fuzz zero and each signed offset
within its corresponding absolute limit. C<[$max_offset...]> is the array
reference returned by C<normalize_udiff>. At least one hunk is required.

Returns the parsed hunk array reference on success; otherwise dies with a
diagnostic. This is also suitable for callers running patch inside their
own sandbox.

=back

=cut

package AnyEvent::MCP;

use common::sense;
use Digest::SHA ();

our $VERSION = '0.0';

sub random_bytes($) {
   my ($length) = @_;

   die "Invalid random byte count\n"
      unless defined $length && $length =~ /\A[0-9]+\z/;
   return "" unless $length;

   my $bytes = "";

   if (open my $fh, "<", "/dev/urandom") {
      binmode $fh;
      while (length $bytes < $length) {
         read ($fh, $bytes, $length - length ($bytes), length $bytes)
            or last;
      }
      close $fh;

      return $bytes if length $bytes == $length;
   }

   if (open my $fh, "-|", "openssl", "rand", $length) {
      binmode $fh;
      local $/;
      $bytes = <$fh>;
      my $success = close $fh;

      return $bytes
         if $success && defined $bytes && length $bytes == $length;
   }

   die "Cannot obtain $length random bytes from /dev/urandom or openssl rand\n";
}

sub hkdf_sha512_expand($$$) {
   my ($prk, $info, $l) = @_;

   64 == length $prk
      or die "hkdf_sha512_expand: prk length mist be 64 octets";

   my $t   = "";
   my $okm = "";
   my $i   = 0;

   do {
      $t = Digest::SHA::hmac_sha512 $t . $info . chr ++$i, $prk;
      $okm .= $t;
   } while $l > length $okm;

   substr $okm, 0, $l
}

sub normalize_udiff {
   my $diff = shift;
   my @line = split /\n/, $diff, -1;
   my $delta = 0;
   my $hunks = 0;
   my @max_offset;

   pop @line while @line and !length $line[-1];

   for (my $i = 0; $i < @line; ++$i) {
      next unless $line[$i] =~ /^@@ /;

      $line[$i] =~ /^@@ -(\d+)(?:,\d+)?(?: \+\d+(?:,\d+)?)? @@(.*)$/
         or die "normalize_udiff: bad hunk header '$line[$i]'\n";

      my ($old_start, $suffix) = ($1, $2);
      my ($old_count, $new_count) = (0, 0);
      my %old_line;
      my $j = $i + 1;

      # GNU patch mishandles hunks with more prefix than suffix context.
      # Make the first context line an identity change without losing it.
      # see https://unix.stackexchange.com/questions/414542/does-patch-work-with-asymmetric-context
      splice @line, $i + 1, 1, "-$1", "+$1"
         if $line[$i + 1] =~ /^ (.*)\z/;

      for (; $j < @line; ++$j) {
         last if $line[$j] =~ /^@@ /;

         my $tag = substr $line[$j], 0, 1;

         if ($tag eq " ") {
            ++$old_count;
            ++$new_count;
            $old_line{substr $line[$j], 1} = 1;
         } elsif ($tag eq "-") {
            ++$old_count;
            $old_line{substr $line[$j], 1} = 1;
         } elsif ($tag eq "+") {
            ++$new_count;
         } elsif ($line[$j] eq "\\ No newline at end of file") {
            # Marker belongs to the preceding body line and counts neither side.
         } else {
            die "normalize_udiff: bad hunk line '$line[$j]'\n";
         }
      }

      $old_count or $new_count
         or die "normalize_udiff: empty hunk at old line $old_start\n";

      $old_count or !$old_start
         or die "normalize_udiff: hunk " . ($hunks + 1)
              . " needs old-side context for insertion after old line $old_start\n";

      my $new_start = $old_start + $delta;
      ++$new_start unless $old_count;
      --$new_start unless $new_count;

      $new_start >= 0
         or die "normalize_udiff: invalid new line $new_start\n";

      $line[$i] = sprintf "@@ -%d,%d +%d,%d @@%s",
         $old_start, $old_count, $new_start, $new_count, $suffix;

      $delta += $new_count - $old_count;
      ++$hunks;
      my $max_offset = keys %old_line;
      --$max_offset
         if $max_offset;
      push @max_offset, $max_offset;
      $i = $j - 1;
   }

   $hunks
      or die "normalize_udiff: no hunks\n";

   (join ("\n", @line, ""), \@max_offset)
}

sub parse_patch_output {
   my ($output) = @_;
   my (@hunks, @unparsed);

   for (split /\n/, $output) {
      if (/^Hunk #(\d+) (succeeded|FAILED|ignored) at (-?\d+)(?: with fuzz (\d+))?(?: \(offset (-?\d+) lines?\))?\.\z/) {
         push @hunks, {
            hunk    => 0 + $1,
            success => $2 eq "succeeded",
            line    => 0 + $3,
            fuzz    => 0 + $4,
            offset  => 0 + $5,
         };
      } elsif (!length
         || /^Hmm\.\.\. +Looks like a unified diff to me\.\.\.\z/
         || /^The text leading up to this was:\z/
         || /^-+\z/ || /^\|/
         || /^patching file / || /^checking file /
         || /^Using Plan [AB]\.\.\.\z/ || /^done\z/) {
         # GNU patch --verbose framing, not hunk results.
      } else {
         push @unparsed, $_;
      }
   }

   { hunks => \@hunks, unparsed => \@unparsed }
}

sub check_patch_output {
   my ($status, $output, $max_offset) = @_;
   my $parsed = parse_patch_output $output;
   my $hunks = $parsed->{hunks};

   die "patch failed (wait status $status):\n$output"
      if $status;
   die "patch: unrecognized output:\n" . (join "\n", @{$parsed->{unparsed}}) . "\n"
      if @{$parsed->{unparsed}};
   die "patch: expected " . @$max_offset . " hunks, got " . @$hunks . "\n"
      unless @$hunks == @$max_offset && @$hunks;

   for my $i (0 .. $#$hunks) {
      my $hunk = $hunks->[$i];

      die "patch: unexpected hunk number $hunk->{hunk}\n"
         unless $hunk->{hunk} == $i + 1;
      die "patch: hunk $hunk->{hunk} failed\n"
         unless $hunk->{success};
      die "patch: hunk $hunk->{hunk} used fuzz $hunk->{fuzz}\n"
         if $hunk->{fuzz};
      die "patch: hunk $hunk->{hunk} offset $hunk->{offset} exceeds $max_offset->[$i]\n"
         if abs $hunk->{offset} > $max_offset->[$i];
   }

   $hunks
}

sub apply_udiff {
   my ($input, $output, $diff) = @_;
   my ($normalized, $max_offset) = normalize_udiff $diff;

   require AnyEvent::Util;
   require File::Spec;
   require File::Basename;
   require Fcntl;

   $input  = File::Spec->rel2abs ($input);
   $output = File::Spec->rel2abs ($output);
   my $directory = File::Basename::dirname ($output);

   sysopen my $fh, $output, Fcntl::O_WRONLY () | Fcntl::O_CREAT () | Fcntl::O_EXCL (), 0600
      or die "$output: $!\n";
   close $fh or do { my $error = $!; unlink $output; die "$output: $error\n" };

   my $cv = AE::cv ();
   my $log;
   my $process = eval {
      AnyEvent::Util::run_cmd ([
         "patch", "--verbose", "--batch", "--forward", "--binary", "--fuzz=0",
         "--no-backup-if-mismatch", "--reject-file=-", "--output=$output", "--", $input,
      ],
         "<" => \$normalized,
         ">" => \$log,
         close_all => 1,
         on_prepare => sub {
            $ENV{LC_ALL} = "C";
            chdir $directory or die "$directory: $!\n";
            defined POSIX::dup2 (1, 2) or die "dup2: $!\n";
         },
      );
   };

   if ($@) {
      my $error = $@;
      unlink $output;
      die $error;
   }

   $process->cb (sub {
      my $hunks;
      eval { $hunks = check_patch_output $_[0]->recv, $log, $max_offset; 1 } or do {
         my $error = $@;
         unlink $output;
         $cv->croak ($error);
         return;
      };

      $cv->send ($hunks);
   });

   $cv
}

sub _clean_text($) {
   my ($text) = @_;

   my ($prefix) = (join "\n", grep /\S/, split /\n/, $text)
      =~ /\A([ \t]*)[^\n]*(?:\n\1[^\n]*)*\z/;

   $text =~ s/^\Q$prefix\E//mg;
   $text =~ s/\A\s+//;
   $text =~ s/\s+\z//;
   $text
}

package AnyEvent::MCP::Base;

sub new {
   my ($class, %kv) = @_;
   bless \%kv, $class
}

sub event {
   my ($self, $event, @args) = @_;
   ($self->{"on_$event"} or return)->($self, @args)
}

=head1 SEE ALSO

L<AnyEvent>, L<https://modelcontextprotocol.io/>

=head1 AUTHOR

The main author of this module is OpenAI ChatGPT.

Additional guidance received by:

   Marc Lehmann <schmorp@schmorp.de>
   http://home.schmorp.de/

=cut

1

Revision:	1.6
Committed:	Thu Oct 8 02:03:51 2026 UTC (5 weeks, 1 day ago) by root
Branch:	MAIN
Changes since 1.5:	+92 -39 lines
Log Message:	* empty log message *
#	User	Rev	Content
1	root	1.1	=head1 NAME
2
3			AnyEvent::MCP - Model Context Protocol client/server support
4
5			=head1 SYNOPSIS
6
7	root	1.6	use AnyEvent::MCP::Server::Simple ();
8	root	1.1
9			mcp_tool ...
10	root	1.3	mcp_start;
11	root	1.1
12			or use the object interface directly:
13
14	root	1.6	use AnyEvent::MCP::Server ();
15	root	1.1
16			my $server = AnyEvent::MCP::Server->new (...);
17
18			=head1 DESCRIPTION
19
20			AnyEvent::MCP provides event-driven Model Context Protocol client and server
21			support.
22
23			The usual way to implement a small MCP server is
24			L<AnyEvent::MCP::Server::Simple>, which provides a function-based interface and
25			creates the underlying server objects when a transport such as stdio or HTTP is
26			started.
27
28			The lower-level object interfaces are intended for applications that need to
29			manage MCP connections, servers or reusable tool registries directly.
30
31			=head2 MODULES
32
33			=over 4
34
35			=item L<AnyEvent::MCP::Server::Simple>
36
37			Function-based interface for implementing ordinary MCP servers.
38
39			=item L<AnyEvent::MCP::Server>
40
41			Object-oriented MCP server interface.
42
43			=item L<AnyEvent::MCP::Client>
44
45			Object-oriented MCP client interface.
46
47			=item L<AnyEvent::MCP::Server::Toolset>
48
49			Reusable registry of MCP tool declarations.
50
51			=item L<AnyEvent::MCP::Server::Permissions>
52
53			Permission and capability handling for MCP servers.
54
55			=back
56
57	root	1.4	C<mcp-multibroker> combines downstream HTTP and stdio servers under tool-name
58			prefixes. It uses the same client, server and permission helper facilities,
59			including modern input forwarding and local permission prompts for legacy
60			callers. Run C<mcp-multibroker --help> for command-line syntax; its manual
61			describes authentication and configuration.
62
63	root	1.1	The interfaces are still being designed; this documentation is intentionally
64			only an overview for now.
65
66	root	1.2	=head1 GLOBAL CONFIGURATION
67
68			The shared per-user configuration is C<$XDG_CONFIG_HOME/anyevent-mcp/global.ini>,
69			or C<$HOME/.config/anyevent-mcp/global.ini> when XDG_CONFIG_HOME is unset.
70			L<AnyEvent::MCP::Config> loads and holds it; loading this module does not access
71			configuration files.
72
73			The file is UTF-8 and uses sections with single-line C<key = value> pairs.
74			Values are unquoted strings. Blank lines and whole-line comments beginning
75			with C<#> or C<;> are ignored; inline comment characters remain part of the
76			value. Later occurrences of a key replace earlier ones in the same section.
77
78			[global]
79			secret = ...128 hexadecimal digits...
80
81			[server example]
82	root	1.3	port = 31740
83			url = https://example.net:31740/{cookie}/
84	root	1.2
85			[mcp-fs]
86			utility = /path/to/utility
87
88			Section names are unrestricted. Application-specific sections, including
89			exports, utility paths and user settings, are documented by their applications.
90
91			C<[global]> holds C<secret>, a 64-byte master key encoded as 128 hexadecimal
92			digits. The file must be owned by the current user, with no group or other
93			permissions. A missing secret is generated automatically on first configuration
94			access and saved when possible. Existing secrets are never replaced implicitly.
95			An invalid secret is an error.
96
97			If saving fails, Config warns and retains the secret in memory. Credentials
98			then remain stable only for that process; other processes cannot derive the
99			same credentials. If randomness is unavailable, supply a securely generated
100			secret in the file.
101
102			C<[server NAME]> holds named-server settings. Its C<url> is a complete template;
103			C<{cookie}> is replaced with the cookie derived for that server and optional
104			username. Scheme, host, port and cookie placement are explicit in the template.
105	root	1.3	HTTP servers with an explicit C<name> load C<host>, C<port>, C<path>,
106			C<url_host>, C<url_scheme>, C<cookie>, C<bearer> and C<users> from this section
107			as defaults. C<users> is a comma-separated allowlist whose Basic passwords
108			are derived for the named server. An explicit password hash can instead be
109			passed to the constructor. C<url> is a template for the utility program; it
110			does not set the listener's address.
111
112			C<mcp_start> chooses an application name and supplies cookie/bearer
113			authentication by default. Explicit authentication settings replace this
114			default. Stdio startup does not access global configuration.
115
116			C<[client NAME]> supplies HTTP client defaults: C<url>, C<bearer>, C<username>,
117			C<password> and C<timeout>. Clients consult it only when explicitly given a
118			C<name>. An unnamed client or HTTP server does not read global configuration.
119			Explicit constructor arguments take precedence over named defaults.
120
121			=head1 ENVIRONMENT
122
123			Project-specific environment variables use the C<PERL_ANYEVENT_MCP_> prefix.
124			C<PERL_ANYEVENT_MCP_MULTIBROKER_PROTOCOL=stdio> selects stdio in Simple.
125			C<PERL_ANYEVENT_MCP_MULTIBROKER_ALIAS> supplies the default application name.
126			C<PERL_ANYEVENT_MCP_PERMISSION_HELPER> selects the external asking executable.
127			Standard C<HOME> and C<XDG_CONFIG_HOME> keep their standard names.
128	root	1.2
129			=head1 FUNCTIONS
130
131	root	1.6	=over
132
133			=item $bytes = AnyEvent::MCP::random_bytes $length
134	root	1.2
135			Returns exactly C<$length> random bytes. Tries C</dev/urandom>, then an external
136			C<openssl rand> command. No additional random-number module is required.
137			Dies if neither source supplies the requested bytes successfully.
138			C<$length> must be a nonnegative integer; zero returns an empty string.
139
140	root	1.6	=back
141
142			=head2 PATCH UTILITIES
143
144			Since applying patches to files is a common taks for MCP servers, the
145			following utility functions can be used to ease that job. Together, they
146			define a ocmmon patch format (unified diff or a simplified version of it,
147			with fewer requirements to make mto easier for the LLM to generate), helpers
148			to apply the patch and a helper to verify if the patch was applied
149			with sufficient precision.
150
151			The workflow would be:
152
153			=over
154
155			=item 1. AnyEvent::MCP::normalize_udiff
156
157			Retursn a unified diff for GNU patch, and meta data to verify its application.
158
159			=item 2. AnyEvent::MCP::apply_udiff
160
161			This should capture GNU patch output.
162	root	1.5
163	root	1.6	=back
164
165			If you apply the patch yourself, you should capture patch otuput, parse it
166			via C<parse_patch_output> and check limits via C<check_patch_output>.
167	root	1.5
168			=head3 Input format
169
170	root	1.6	The patch format accepted by normalize_udiff is an extension to the
171			(essentially undocumented) unified diff format.
172
173	root	1.5	In a hunk header, only the old start C<-N> matters. It is the old-file line
174			of the first hunk body line, including context, not necessarily the first
175			changed line. Counts and the new-file position are ignored and recomputed.
176			Both ordinary headers and the abbreviated form are accepted:
177
178			@@ -42,99 +123,99 @@
179			@@ -42 @@
180
181			Optional text after the closing C<@@> is preserved. File headers and other
182			text before the first hunk are preserved; a diff must describe one file.
183
184			Hunk body lines use the usual prefixes: a space for unchanged context,
185			C<-> for removed lines and C<+> for added lines. The
186			C<\ No newline at end of file> marker is preserved and counts neither side.
187			Trailing empty lines outside the final hunk are discarded.
188
189			Pure insertion is permitted only at the beginning, using old start zero.
190			An insertion elsewhere needs old-side context. Empty hunks are rejected.
191			New positions include the cumulative line-count changes of preceding hunks.
192
193			=head3 Applying the result
194
195	root	1.6	The C<normalize_udiff> function does not apply the patch, check file
196			contents or guard against concurrent edits. The caller must supply those
197			checks, if required.
198	root	1.5
199			Context must match exactly: apply with fuzz zero. For each hunk,
200			C<$max_offset> permits relocation by at most the number of distinct old-side
201			lines minus one, or zero for a pure insertion. Repeated old-side lines do
202			not increase this allowance. The applier must enforce these limits; an
203			unrestricted search for matching context can select the wrong occurrence.
204
205			For live Vim buffers, also require the expected changedtick to match.
206			File-based users need an equivalent check before replacing the file.
207
208	root	1.6	To work around GNU patch's handling of asymmetric context, the
209			first context line of each hunk is rewritten as an identity
210			removal/addition. The line contents and old/new line counts are
211			unchanged. This is normalization for the patch applier, not a relaxation
212			of context matching.
213	root	1.5
214	root	1.6	=over
215
216			=item ($diff, $max_offset) = AnyEvent::MCP::normalize_udiff $diff
217
218			Normalizes a relaxed, single-file unified diff into ordinary unified diff
219			syntax. Returns the normalized C<$diff> and an array reference C<$max_offset>
220			containing the permitted whole-hunk relocation for each hunk, in order.
221			Dies on malformed hunks or when no hunks are found.
222
223			Here is a suitable description for the diff format, e.g. in a tool
224			definition:
225
226			Apply a unified diff to one regular file. Hunk counts are recomputed,
227			fuzz is disabled, whole-hunk relocation is limited per hunk by distinct
228			old-side lines. Pure insertion is allowed only at the beginning;
229			elsewhere include old-side context.
230
231			=item $cv = AnyEvent::MCP::apply_udiff $input, $output, $diff
232
233			Asynchronously applies the relaxed C<$diff> to the input file C<$input>,
234			writing a separate output file C<$output>. C<$diff> must contain bytes;
235			callers working with characters must encode them for the file themselves.
236
237			Normalizes the diff, runs GNU patch using C<AnyEvent::Util::run_cmd>, and
238			validates its verbose output with C<check_patch_output>. The command uses
239			batch/forward mode, binary mode and fuzz zero. No shell is involved.
240
241			C<$output> must not exist. It is reserved with mode 0600; patch runs in its
242			directory so incidental temporary files stay there. Input and output paths
243			are made absolute before starting the command. These must be trusted paths
244			in a directory controlled by the caller.
245
246			Returns a condition variable. Its C<recv> returns the validated hunk array
247			reference, or throws on command/application failure. Setup failures throw
248			synchronously. Failed or partial output is removed. C<$input> is unchanged.
249
250			The caller owns committing the successful output and removing it when no
251			longer needed. Freshness checks, metadata preservation, atomic replacement
252			and application-specific permissions also belong to the caller.
253
254			For your reference, the exact options used are:
255
256			--verbose --batch --forward --binary --fuzz=0
257			--no-backup-if-mismatch
258			--reject-file=- --output=... -- <inputfile>
259
260			=item $parsed = AnyEvent::MCP::parse_patch_output $output
261	root	1.5
262			Parses C<LC_ALL=C> GNU patch C<--verbose> output without judging whether
263			the application is acceptable. C<$parsed> has two fields:
264
265	root	1.6	=over
266	root	1.5
267			=item hunks => [$hunk...]
268
269			Hunk records in output order. Each record contains C<hunk> (the one-based
270			number), C<success>, C<line> (the reported application line), C<fuzz> and
271			the signed C<offset>. Omitted fuzz and offset are zero. Failed and ignored
272			hunks have false C<success>.
273
274			=item unparsed => [$line...]
275
276			Lines not recognized as hunk results or GNU patch's verbose framing.
277			The parser preserves them for callers to interpret or reject.
278
279			=back
280
281			Use verbose output: ordinary patch output omits exact-position successes,
282			so it cannot account for every hunk.
283
284	root	1.6	=item $hunks = AnyEvent::MCP::check_patch_output $status, $output, [$max_offset...]
285	root	1.5
286			Parses C<$output> and validates a complete application. C<$status> is the
287			raw process wait status, as returned by C<waitpid> or
288			C<AnyEvent::Util::run_cmd>, not just the exit code.
289
290			Requires status zero, no unrecognized output, exactly the expected hunks
291			in numbered order, successful application, fuzz zero and each signed offset
292			within its corresponding absolute limit. C<[$max_offset...]> is the array
293			reference returned by C<normalize_udiff>. At least one hunk is required.
294
295			Returns the parsed hunk array reference on success; otherwise dies with a
296			diagnostic. This is also suitable for callers running patch inside their
297			own sandbox.
298
299	root	1.6	=back
300	root	1.5
301	root	1.1	=cut
302
303			package AnyEvent::MCP;
304
305			use common::sense;
306			use Digest::SHA ();
307
308			our $VERSION = '0.0';
309
310	root	1.2	sub random_bytes($) {
311			my ($length) = @_;
312
313			die "Invalid random byte count\n"
314			unless defined $length && $length =~ /\A[0-9]+\z/;
315			return "" unless $length;
316
317			my $bytes = "";
318
319			if (open my $fh, "<", "/dev/urandom") {
320			binmode $fh;
321			while (length $bytes < $length) {
322			read ($fh, $bytes, $length - length ($bytes), length $bytes)
323			or last;
324			}
325			close $fh;
326
327			return $bytes if length $bytes == $length;
328			}
329
330			if (open my $fh, "-\|", "openssl", "rand", $length) {
331			binmode $fh;
332			local $/;
333			$bytes = <$fh>;
334			my $success = close $fh;
335
336			return $bytes
337			if $success && defined $bytes && length $bytes == $length;
338			}
339
340			die "Cannot obtain $length random bytes from /dev/urandom or openssl rand\n";
341			}
342
343	root	1.1	sub hkdf_sha512_expand($$$) {
344			my ($prk, $info, $l) = @_;
345
346	root	1.2	64 == length $prk
347			or die "hkdf_sha512_expand: prk length mist be 64 octets";
348
349	root	1.1	my $t = "";
350			my $okm = "";
351			my $i = 0;
352
353			do {
354			$t = Digest::SHA::hmac_sha512 $t . $info . chr ++$i, $prk;
355			$okm .= $t;
356			} while $l > length $okm;
357
358			substr $okm, 0, $l
359			}
360
361	root	1.5	sub normalize_udiff {
362			my $diff = shift;
363			my @line = split /\n/, $diff, -1;
364			my $delta = 0;
365			my $hunks = 0;
366			my @max_offset;
367
368			pop @line while @line and !length $line[-1];
369
370			for (my $i = 0; $i < @line; ++$i) {
371			next unless $line[$i] =~ /^@@ /;
372
373			$line[$i] =~ /^@@ -(\d+)(?:,\d+)?(?: \+\d+(?:,\d+)?)? @@(.*)$/
374			or die "normalize_udiff: bad hunk header '$line[$i]'\n";
375
376			my ($old_start, $suffix) = ($1, $2);
377			my ($old_count, $new_count) = (0, 0);
378			my %old_line;
379			my $j = $i + 1;
380
381			# GNU patch mishandles hunks with more prefix than suffix context.
382			# Make the first context line an identity change without losing it.
383			# see https://unix.stackexchange.com/questions/414542/does-patch-work-with-asymmetric-context
384			splice @line, $i + 1, 1, "-$1", "+$1"
385			if $line[$i + 1] =~ /^ (.*)\z/;
386
387			for (; $j < @line; ++$j) {
388			last if $line[$j] =~ /^@@ /;
389
390			my $tag = substr $line[$j], 0, 1;
391
392			if ($tag eq " ") {
393			++$old_count;
394			++$new_count;
395			$old_line{substr $line[$j], 1} = 1;
396			} elsif ($tag eq "-") {
397			++$old_count;
398			$old_line{substr $line[$j], 1} = 1;
399			} elsif ($tag eq "+") {
400			++$new_count;
401			} elsif ($line[$j] eq "\\ No newline at end of file") {
402			# Marker belongs to the preceding body line and counts neither side.
403			} else {
404			die "normalize_udiff: bad hunk line '$line[$j]'\n";
405			}
406			}
407
408			$old_count or $new_count
409			or die "normalize_udiff: empty hunk at old line $old_start\n";
410
411			$old_count or !$old_start
412			or die "normalize_udiff: hunk " . ($hunks + 1)
413			. " needs old-side context for insertion after old line $old_start\n";
414
415			my $new_start = $old_start + $delta;
416			++$new_start unless $old_count;
417			--$new_start unless $new_count;
418
419			$new_start >= 0
420			or die "normalize_udiff: invalid new line $new_start\n";
421
422			$line[$i] = sprintf "@@ -%d,%d +%d,%d @@%s",
423			$old_start, $old_count, $new_start, $new_count, $suffix;
424
425			$delta += $new_count - $old_count;
426			++$hunks;
427			my $max_offset = keys %old_line;
428			--$max_offset
429			if $max_offset;
430			push @max_offset, $max_offset;
431			$i = $j - 1;
432			}
433
434			$hunks
435			or die "normalize_udiff: no hunks\n";
436
437			(join ("\n", @line, ""), \@max_offset)
438			}
439
440			sub parse_patch_output {
441			my ($output) = @_;
442			my (@hunks, @unparsed);
443
444			for (split /\n/, $output) {
445			if (/^Hunk #(\d+) (succeeded\|FAILED\|ignored) at (-?\d+)(?: with fuzz (\d+))?(?: \(offset (-?\d+) lines?\))?\.\z/) {
446			push @hunks, {
447			hunk => 0 + $1,
448			success => $2 eq "succeeded",
449			line => 0 + $3,
450			fuzz => 0 + $4,
451			offset => 0 + $5,
452			};
453			} elsif (!length
454			\|\| /^Hmm\.\.\. +Looks like a unified diff to me\.\.\.\z/
455			\|\| /^The text leading up to this was:\z/
456			\|\| /^-+\z/ \|\| /^\\|/
457			\|\| /^patching file / \|\| /^checking file /
458			\|\| /^Using Plan [AB]\.\.\.\z/ \|\| /^done\z/) {
459			# GNU patch --verbose framing, not hunk results.
460			} else {
461			push @unparsed, $_;
462			}
463			}
464
465			{ hunks => \@hunks, unparsed => \@unparsed }
466			}
467
468			sub check_patch_output {
469			my ($status, $output, $max_offset) = @_;
470			my $parsed = parse_patch_output $output;
471			my $hunks = $parsed->{hunks};
472
473			die "patch failed (wait status $status):\n$output"
474			if $status;
475			die "patch: unrecognized output:\n" . (join "\n", @{$parsed->{unparsed}}) . "\n"
476			if @{$parsed->{unparsed}};
477			die "patch: expected " . @$max_offset . " hunks, got " . @$hunks . "\n"
478			unless @$hunks == @$max_offset && @$hunks;
479
480			for my $i (0 .. $#$hunks) {
481			my $hunk = $hunks->[$i];
482
483			die "patch: unexpected hunk number $hunk->{hunk}\n"
484			unless $hunk->{hunk} == $i + 1;
485			die "patch: hunk $hunk->{hunk} failed\n"
486			unless $hunk->{success};
487			die "patch: hunk $hunk->{hunk} used fuzz $hunk->{fuzz}\n"
488			if $hunk->{fuzz};
489			die "patch: hunk $hunk->{hunk} offset $hunk->{offset} exceeds $max_offset->[$i]\n"
490			if abs $hunk->{offset} > $max_offset->[$i];
491			}
492
493			$hunks
494			}
495
496			sub apply_udiff {
497			my ($input, $output, $diff) = @_;
498			my ($normalized, $max_offset) = normalize_udiff $diff;
499
500			require AnyEvent::Util;
501			require File::Spec;
502			require File::Basename;
503			require Fcntl;
504
505			$input = File::Spec->rel2abs ($input);
506			$output = File::Spec->rel2abs ($output);
507			my $directory = File::Basename::dirname ($output);
508
509			sysopen my $fh, $output, Fcntl::O_WRONLY () \| Fcntl::O_CREAT () \| Fcntl::O_EXCL (), 0600
510			or die "$output: $!\n";
511			close $fh or do { my $error = $!; unlink $output; die "$output: $error\n" };
512
513			my $cv = AE::cv ();
514			my $log;
515			my $process = eval {
516			AnyEvent::Util::run_cmd ([
517			"patch", "--verbose", "--batch", "--forward", "--binary", "--fuzz=0",
518			"--no-backup-if-mismatch", "--reject-file=-", "--output=$output", "--", $input,
519			],
520			"<" => \$normalized,
521			">" => \$log,
522			close_all => 1,
523			on_prepare => sub {
524			$ENV{LC_ALL} = "C";
525			chdir $directory or die "$directory: $!\n";
526			defined POSIX::dup2 (1, 2) or die "dup2: $!\n";
527			},
528			);
529			};
530
531			if ($@) {
532			my $error = $@;
533			unlink $output;
534			die $error;
535			}
536
537			$process->cb (sub {
538			my $hunks;
539			eval { $hunks = check_patch_output $_[0]->recv, $log, $max_offset; 1 } or do {
540			my $error = $@;
541			unlink $output;
542			$cv->croak ($error);
543			return;
544			};
545
546			$cv->send ($hunks);
547			});
548
549			$cv
550			}
551
552	root	1.1	sub _clean_text($) {
553			my ($text) = @_;
554
555			my ($prefix) = (join "\n", grep /\S/, split /\n/, $text)
556			=~ /\A([ \t])[^\n](?:\n\1[^\n])\z/;
557
558			$text =~ s/^\Q$prefix\E//mg;
559			$text =~ s/\A\s+//;
560			$text =~ s/\s+\z//;
561			$text
562			}
563
564			package AnyEvent::MCP::Base;
565
566			sub new {
567			my ($class, %kv) = @_;
568			bless \%kv, $class
569			}
570
571			sub event {
572			my ($self, $event, @args) = @_;
573			($self->{"on_$event"} or return)->($self, @args)
574			}
575
576			=head1 SEE ALSO
577
578			L<AnyEvent>, L<https://modelcontextprotocol.io/>
579
580			=head1 AUTHOR
581
582			The main author of this module is OpenAI ChatGPT.
583
584			Additional guidance received by:
585
586			Marc Lehmann <schmorp@schmorp.de>
587			http://home.schmorp.de/
588
589			=cut
590
591			1
592