github-fetcher

GitHub API GET

github_api_get

Read-onlyIdempotent

Fetch read-only GitHub REST API GET responses for endpoints not covered by dedicated tools; the host is fixed to api.github.com, and writes and GraphQL are unsupported.

Instructions

Escape hatch for read-only GitHub REST GET requests that the dedicated tools do not cover. The host is fixed to api.github.com; GraphQL and writes are not supported.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "path": "<path>"
    },
    "name": "github_api_get"
  }
}

Input Schema

Name	Required	Description	Default
`path`	Yes	Absolute API path, for example /repos/owner/name/readme
`query`	No	Query parameters; entries override pairs already present in path

Schema Changelog

Changes observed during successful MCP inspections.

Changed2 schema fields changedv0.2.1Nov 7, 2026

changedInput schema / properties / query / additionalProperties / type

Previous value: -"string"New value: +[
+  "string",
+  "number",
+  "boolean"
+]

changedInput schema / properties / query / description

Previous value: -"Query string parameters"New value: +"Query parameters; entries override pairs already present in path"

First observedv0.1.0Nov 1, 2026

TDQS

A4.4/5.0

Behavior4/5

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

Annotations already declare readOnlyHint, idempotentHint, destructiveHint=false and openWorldHint, so the safety profile is covered; the description usefully adds the hard constraints that the host is pinned to api.github.com and that GraphQL and write operations are rejected. It does not mention authentication/token usage, rate-limit exposure, or how upstream API errors surface, which are meaningful for an open-world passthrough.

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?

Two sentences, zero waste, with the escape-hatch purpose front-loaded and the hard limits (host, no GraphQL, no writes) following immediately. Nothing needs trimming and nothing is buried.

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

Completeness4/5

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

For a generic passthrough with no output schema, the description covers scope, host pinning, and what is unsupported, which is enough to call it correctly. Rate-limit behavior and auth expectations are the notable omissions, though annotations and the github_rate_limit sibling partially offset them.

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%, and the schema itself documents the absolute path format and that query entries override pairs already present in path. The description adds nothing about either parameter, so the baseline 3 applies - correct, but no value added beyond structured data.

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 states a specific verb and resource ('read-only GitHub REST GET requests') and explicitly frames the tool as an escape hatch for endpoints the dedicated tools do not cover, which distinguishes it from the entire sibling set (github_repo, github_file, github_search_code, etc.). An agent can tell immediately that this is the fallback for uncovered endpoints rather than a replacement for the named 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 gives both sides of the routing decision: use this when the dedicated tools do not cover the endpoint, and do not use it for GraphQL or writes. The host constraint (api.github.com) further bounds where it applies. The only minor gap is that it does not name specific siblings to prefer, but 'dedicated tools' clearly refers to the sibling set.

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