glim.sh

GitHub Search

glim_github_search

Read-onlyIdempotent

Search GitHub repositories, conversations (issues+PRs), discussions, or code, with full GitHub search syntax in the query: qualifiers (repo:, org:/user:, language:, path:, symbol:, content:, is:, stars:, label:, sort:stars), boolean AND/OR/NOT with parentheses, "exact strings", and /regex/. kind='repos': MINIMAL distinctive keywords - the project/library name only ('rtk', 'react query'); every extra word must ALL match and buries the canonical repo - filter with qualifiers, not prose. kind='code': ONE literal code pattern as it appears in files ('useState('), an "exact string", a /regex/, or symbol:name to find definitions, across 2.8M+ public repos; narrow with repo:/language:/path:. Not supported in code search: license:, enterprise:, is:vendored, is:generated. kind='conversations': returns compact previews - use glim_github_get for full content; sort: REPLACES relevance ranking (words match anywhere incl. comments), omit it for best matches. kind='discussions': GitHub Discussions, a SEPARATE index from issues/PRs - a question answered there never appears under conversations, so reach for it when a repo does its Q&A in Discussions; supports repo:/org:/author:/is:answered plus category: (the repo's own category name, needs a repo: scope), up to 10 results per page, no sort:. Set repo='owner/name' to scope to one repository (works with any kind; with repos it routes to conversations). kind is optional - inferred from the query (is:answered/category: -> discussions, is:/label: -> conversations, path:/symbol://regex/ -> code, stars:/topic: -> repos, else repos); a conversations search with no matches is retried as discussions and says so. Returns compact text by default; pass format='json' for full structured data.

Input Schema

TableJSON Schema

Name	Required	Description	Default
`kind`	No	What to search: 'repos', 'conversations' (issues+PRs), 'discussions' (GitHub Discussions - a separate index from issues/PRs), or 'code' (literal/regex/symbol search across 2.8M+ public GitHub repos). Optional - inferred from the query: is:answered/category: implies discussions, is:/label:/author: implies conversations, path:/symbol:/content://regex/ implies code, stars:/topic:/in:readme implies repos, otherwise repos. type:code / type:repos / type:discussions in the query also works. A conversations search that matches nothing is retried as discussions, so an answer that lives in Discussions is not silently missed.
`page`	No	Page number
`repo`	No	Scope to one repository. Accepts 'owner/name', a github.com URL, or a partial 'owner/' (code). Works with any kind; setting it with kind=repos routes the search to conversations, since repo-name search can't scope to one repo. Equivalent to a repo: qualifier in the query (if both are given they must match).
`query`	Yes	Search query in full GitHub search syntax: qualifiers (repo:owner/name, org:/user:, language:, path: with globs, symbol:, content:, is:, stars:>N, label:, sort:stars), boolean AND/OR/NOT with parentheses, "exact strings", and /regex/. kind=repos: minimal distinctive keywords - the project/library name (GOOD: 'rtk', 'react query'; BAD: 'rtk rust token killer' - every extra word must ALL match and buries the real repo; filter with qualifiers, not prose). kind=code: ONE literal code pattern as it appears in files ('useState('), an "exact string", a /regex/, or symbol:name for definitions; narrow with repo:/language:/path:, not extra words. kind=conversations: keywords plus filters (is:issue, label:bug). kind=discussions: keywords plus repo:/org:/author:/is:answered/category: - a separate GitHub index from issues/PRs, so a thread that lives in Discussions is invisible to kind=conversations (and vice versa). category: matches the repo's own category name (Ideas, Q&A) and needs a repo: scope; sort: does not apply. Caution: sort: REPLACES relevance ranking (sort:reactions = most-popular thread mentioning the words anywhere, incl. comments) - omit sort: for best-match. Not supported in code search: license:, enterprise:, is:vendored, is:generated.
`format`	No	Output format. 'text' (default): compact human-readable previews, fewer tokens. 'json': full structured data for machine parsing.	text
`per_page`	No	Results per page

Schema Changelog

Changes observed during successful MCP inspections.

Changed3 schema fields changedAug 28, 2026

changedInput schema / properties / kind / description

Previous value: -"What to search: 'repos', 'conversations' (issues+PRs), or 'code' (literal/regex/symbol search across 2.8M+ public GitHub repos). Optional - inferred from the query: is:/label:/author: implies conversations, path:/symbol:/content://regex/ implies code, stars:/topic:/in:readme implies repos, otherwise repos. type:code / type:repos in the query also works."New value: +"What to search: 'repos', 'conversations' (issues+PRs), 'discussions' (GitHub Discussions - a separate index from issues/PRs), or 'code' (literal/regex/symbol search across 2.8M+ public GitHub repos). Optional - inferred from the query: is:answered/category: implies discussions, is:/label:/author: implies conversations, path:/symbol:/content://regex/ implies code, stars:/topic:/in:readme implies repos, otherwise repos. type:code / type:repos / type:discussions in the query also works. A conversations search that matches nothing is retried as discussions, so an answer that lives in Discussions is not silently missed."

changedInput schema / properties / kind / enum

Previous value: -[
-  "repos",
-  "conversations",
-  "code"
-]New value: +[
+  "repos",
+  "conversations",
+  "code",
+  "discussions"
+]

changedInput schema / properties / query / description

Previous value: -"Search query in full GitHub search syntax: qualifiers (repo:owner/name, org:/user:, language:, path: with globs, symbol:, content:, is:, stars:>N, label:, sort:stars), boolean AND/OR/NOT with parentheses, \"exact strings\", and /regex/. kind=repos: minimal distinctive keywords - the project/library name (GOOD: 'rtk', 'react query'; BAD: 'rtk rust token killer' - every extra word must ALL match and buries the real repo; filter with qualifiers, not prose). kind=code: ONE literal code pattern as it appears in files ('useState('), an \"exact string\", a /regex/, or symbol:name for definitions; narrow with repo:/language:/path:, not extra words. kind=conversations: keywords plus filters (is:issue, label:bug). Caution: sort: REPLACES relevance ranking (sort:reactions = most-popular thread mentioning the words anywhere, incl. comments) - omit sort: for best-match. Not supported in code search: license:, enterprise:, is:vendored, is:generated."New value: +"Search query in full GitHub search syntax: qualifiers (repo:owner/name, org:/user:, language:, path: with globs, symbol:, content:, is:, stars:>N, label:, sort:stars), boolean AND/OR/NOT with parentheses, \"exact strings\", and /regex/. kind=repos: minimal distinctive keywords - the project/library name (GOOD: 'rtk', 'react query'; BAD: 'rtk rust token killer' - every extra word must ALL match and buries the real repo; filter with qualifiers, not prose). kind=code: ONE literal code pattern as it appears in files ('useState('), an \"exact string\", a /regex/, or symbol:name for definitions; narrow with repo:/language:/path:, not extra words. kind=conversations: keywords plus filters (is:issue, label:bug). kind=discussions: keywords plus repo:/org:/author:/is:answered/category: - a separate GitHub index from issues/PRs, so a thread that lives in Discussions is invisible to kind=conversations (and vice versa). category: matches the repo's own category name (Ideas, Q&A) and needs a repo: scope; sort: does not apply. Caution: sort: REPLACES relevance ranking (sort:reactions = most-popular thread mentioning the words anywhere, incl. comments) - omit sort: for best-match. Not supported in code search: license:, enterprise:, is:vendored, is:generated."

Changed1 schema field changedJun 12, 2026

changedInput schema / properties / query / description

Previous value: -"Search query in full GitHub search syntax: qualifiers (repo:owner/name, org:/user:, language:, path: with globs, symbol:, content:, is:, stars:>N, label:, sort:stars), boolean AND/OR/NOT with parentheses, \"exact strings\", and /regex/. kind=repos: minimal distinctive keywords - the project/library name (GOOD: 'rtk', 'react query'; BAD: 'rtk rust token killer' - every extra word must ALL match and buries the real repo; filter with qualifiers, not prose). kind=code: ONE literal code pattern as it appears in files ('useState('), an \"exact string\", a /regex/, or symbol:name for definitions; narrow with repo:/language:/path:, not extra words. kind=conversations: keywords plus filters (is:issue, label:bug, sort:reactions). Not supported in code search: license:, enterprise:, is:vendored, is:generated."New value: +"Search query in full GitHub search syntax: qualifiers (repo:owner/name, org:/user:, language:, path: with globs, symbol:, content:, is:, stars:>N, label:, sort:stars), boolean AND/OR/NOT with parentheses, \"exact strings\", and /regex/. kind=repos: minimal distinctive keywords - the project/library name (GOOD: 'rtk', 'react query'; BAD: 'rtk rust token killer' - every extra word must ALL match and buries the real repo; filter with qualifiers, not prose). kind=code: ONE literal code pattern as it appears in files ('useState('), an \"exact string\", a /regex/, or symbol:name for definitions; narrow with repo:/language:/path:, not extra words. kind=conversations: keywords plus filters (is:issue, label:bug). Caution: sort: REPLACES relevance ranking (sort:reactions = most-popular thread mentioning the words anywhere, incl. comments) - omit sort: for best-match. Not supported in code search: license:, enterprise:, is:vendored, is:generated."

Changed5 schema fields changedJun 12, 2026

changedInput schema / properties / kind / description

Previous value: -"What to search: 'repos', 'conversations' (issues+PRs), or 'code' (literal code patterns across 1M+ public GitHub repos). Optional - omit to let it be inferred from the query: a repo: scope or is:/label:/author: qualifier implies conversations, a path: qualifier implies code, otherwise repos."New value: +"What to search: 'repos', 'conversations' (issues+PRs), or 'code' (literal/regex/symbol search across 2.8M+ public GitHub repos). Optional - inferred from the query: is:/label:/author: implies conversations, path:/symbol:/content://regex/ implies code, stars:/topic:/in:readme implies repos, otherwise repos. type:code / type:repos in the query also works."

removedInput schema / properties / order

Removed value: -{
-  "default": "desc",
-  "description": "Sort direction (default: desc)",
-  "enum": [
-    "desc",
-    "asc"
-  ],
-  "type": "string"
-}

changedInput schema / properties / query / description

Previous value: -"Search query. kind=repos: minimal distinctive keywords - the project/library name. GOOD: 'rtk', 'react state management', 'langchain'. BAD: 'rtk rust token killer', 'fast cli that reduces llm tokens' (natural-language phrases match copycat repos and exclude the real project). Add qualifiers to filter, not extra words: language:rust, stars:>500, topic:cli, user:facebook, in:readme. kind=code: a literal code pattern as it appears in files (e.g. 'createServerFn'), NOT keywords or questions; to narrow, append language:/path: qualifiers (e.g. 'useState( language:tsx path:src/') or use the repo param - they are extracted automatically, so do not add descriptive words."New value: +"Search query in full GitHub search syntax: qualifiers (repo:owner/name, org:/user:, language:, path: with globs, symbol:, content:, is:, stars:>N, label:, sort:stars), boolean AND/OR/NOT with parentheses, \"exact strings\", and /regex/. kind=repos: minimal distinctive keywords - the project/library name (GOOD: 'rtk', 'react query'; BAD: 'rtk rust token killer' - every extra word must ALL match and buries the real repo; filter with qualifiers, not prose). kind=code: ONE literal code pattern as it appears in files ('useState('), an \"exact string\", a /regex/, or symbol:name for definitions; narrow with repo:/language:/path:, not extra words. kind=conversations: keywords plus filters (is:issue, label:bug, sort:reactions). Not supported in code search: license:, enterprise:, is:vendored, is:generated."

changedInput schema / properties / repo / description

Previous value: -"Scope to one repository. Accepts 'owner/name', a github.com URL, or a partial 'owner/' (code). Works with any kind - setting it with kind=repos routes to conversations, since repo-name search can't scope to one repo."New value: +"Scope to one repository. Accepts 'owner/name', a github.com URL, or a partial 'owner/' (code). Works with any kind; setting it with kind=repos routes the search to conversations, since repo-name search can't scope to one repo. Equivalent to a repo: qualifier in the query (if both are given they must match)."

removedInput schema / properties / sort

Removed value: -{
-  "default": "best-match",
-  "description": "Sort field. Repos: stars, forks, updated, help-wanted-issues. Conversations: comments, reactions, interactions, created, updated. Default: best-match (relevance). Tip: use sort=stars with a date filter for trending repos.",
-  "enum": [
-    "best-match",
-    "stars",
-    "forks",
-    "updated",
-    "help-wanted-issues",
-    "comments",
-    "reactions",
-    "interactions",
-    "created"
-  ],
-  "type": "string"
-}

First observedJun 11, 2026

TDQS

A4.8/5.0

Behavior5/5

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

Beyond the readOnly/idempotent/destructive annotations, the description discloses important runtime behavior: kind inference, automatic retry of conversations as discussions, the separate index for GitHub Discussions, unsupported code-search qualifiers, and the compact-vs-JSON output default. These are exactly the kind of non-obvious behaviors an agent needs to know before calling.

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

Conciseness4/5

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

The description is long, but the tool genuinely has four query modes and many qualifiers, so the density is largely warranted. It is front-loaded with the core purpose and then organized by kind. However, several points (kind inference, sort: caution, unsupported qualifiers) appear both in the top-level description and in parameter descriptions, adding mild redundancy.

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 multi-mode search tool with no output schema, the description covers the full contract: what each kind searches, how the query is parsed, which qualifiers are unsupported, how repo scoping behaves, pagination, output format, and the fallback retry behavior. Nothing needed for correct selection or invocation is missing.

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

Parameters4/5

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

Schema coverage is 100%, so the baseline is already 3; the description clearly exceeds it by adding concrete query examples ('rtk', 'react query', 'useState('), qualifier guidance, and kind-inference rules. It repeats some of what the schema already says, but the added examples and exclusions meaningfully improve correct parameter construction.

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 by naming the exact scope: 'Search GitHub repositories, conversations (issues+PRs), discussions, or code, with full GitHub search syntax.' The four kinds are enumerated and contrasted, and the relationship to glim_github_get is made clear by saying conversations return compact previews and to 'use glim_github_get for full content.' This lets an agent immediately distinguish it from sibling get/search 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 provides explicit routing guidance: kind='discussions' when a repo does Q&A in Discussions, kind='repos' requires minimal keywords, and kind='conversations' with no matches is retried as discussions. It also names the sibling alternative (glim_github_get) and gives cautionary context around sort: replacing relevance ranking. The agent is never left guessing when to use which mode.

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

All glim.sh tools Inspect

Try in Browser

One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

GitHub Search

Input Schema

Schema Changelog

TDQS

Glama MCP Gateway

Resources