Skip to main content
Glama
brechanbech

forgejo-mcp-rs

by brechanbech
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Rust
Remote

Search repositories

search_repos
Read-only

Search repositories visible to your token, including private ones, by keyword in names or topics, optionally matching descriptions; get paginated results with total match counts.

Instructions

Find repositories anywhere on the instance by keyword: a case-insensitive substring of the repo name or one of its topics (include_description=true widens it to descriptions; owner names are not searched). Covers every repo this token can see, private ones included. Results come alphabetically by name, not ranked by relevance, one page at a time (set limit, up to 50, and page), in list_my_repos' slim shape (full_name, description, private, stars, size, urls, dates), with total giving the full match count. Use list_my_repos for your own repos, get_repo when you already know owner/repo, and list_orgs for the organizations you belong to.

Input Schema

NameRequiredDescriptionDefault
pageNo1-based page number.
limitNoResults per page. Without it Codeberg returns 30 and gitea.com 10; both cap it at 50.
queryYesKeyword, matched case-insensitively as a substring of repository names and topics (`mcp` finds `forgejo-mcp-rs` and a repo tagged `mcp23017`). Not owner names.
include_descriptionNoAlso match the keyword in repository descriptions. Defaults to false; on Codeberg it widened a search for `mcp` from 783 matches to 919.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed3 schema fields changedv0.27.0
    • addedInput schema / properties / include_description
      Added value: +{
+  "default": null,
+  "description": "Also match the keyword in repository descriptions. Defaults to false; on Codeberg it\nwidened a search for `mcp` from 783 matches to 919.",
+  "type": [
+    "boolean",
+    "null"
+  ]
+}
    • changedInput schema / properties / limit / description
      Previous value: -"Results per page."New value: +"Results per page. Without it Codeberg returns 30 and gitea.com 10; both cap it at 50."
    • changedInput schema / properties / query / description
      Previous value: -"Search query (keywords; matches repository names and, by default, descriptions)."New value: +"Keyword, matched case-insensitively as a substring of repository names and topics\n(`mcp` finds `forgejo-mcp-rs` and a repo tagged `mcp23017`). Not owner names."
  2. First observedv0.22.0

TDQS

A4.7/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

Annotations only declare readOnlyHint=true and openWorldHint=true. The description adds substantial behavioral context beyond those: search covers every repo the token can see including private ones, results are alphabetical rather than relevance-ranked, pagination is one page at a time with limit up to 50, and the result shape includes a total match count.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is dense but front-loaded: purpose and matching rules come first, then scope, ordering/pagination, return shape, and sibling alternatives. Every sentence adds useful information for invoking or selecting the tool, with no filler.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a read-only search tool with rich schema coverage and no output schema, the description supplies everything an agent needs: matching rules, scope, result ordering, pagination behavior, return fields via reference to list_my_repos, total count, and when to use alternatives.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema description coverage is 100%, so all four parameters are already documented in the input schema, including query matching rules, include_description behavior, limit defaults/caps, and page numbering. The description reinforces some of this but adds little parameter meaning beyond what the schema already provides, so the high-coverage baseline of 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb and resource: 'Find repositories anywhere on the instance by keyword.' It precisely defines matching behavior (case-insensitive substring of repo name or topics, with optional description matching) and scope (all repos visible to the token, including private), making it clearly distinguishable from sibling tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines5/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

It explicitly routes the agent away from this tool in three named cases: use list_my_repos for your own repos, get_repo when owner/repo is already known, and list_orgs for organizations. This is exactly the when-to-use versus alternatives guidance required.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Deploy Server

Other Tools