Skip to main content
Glama

captapi

by io.github.CDCStream
OverviewDiscussionsAdmin

github_repositories

List a user's repos with sort/direction/type — opaque Link cursor (~0.4/repo). Costs ~12 credits (0.4/result). Empty results and failures are never charged. Pass cache=true for a free 24h cache hit (default always fresh).

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
sortNocreated | updated | pushed | full_name (default updated). Not stars — GitHub's user-repos API has no stars sort. Echoed as data.sort.
typeNoowner (default) | member | all — affiliation filter. Echoed as data.type.
cacheNoSet true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh.
limitNoMax items to return (default 30, max 100). Billed per result.
cursorNoOpaque cursor from a previous nextCursor (GitHub Link page=). Not a bare page number.
usernameYesGitHub username or profile URL, e.g. torvalds.
directionNoasc or desc (default desc). Echoed as data.direction.

Schema Changelog

Changes observed during successful MCP inspections.

  1. Changed1 schema field changed
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh."
  2. Changed7 schema fields changed
    • changedInput schema / properties / cache / description
      Previous value: -"Set true to serve from the 24h response cache. Default false — always fetch fresh data."New value: +"Set true to serve from the 24h response cache (0 credits on hit). Default false — always fetch fresh. Envelope includes cached + cachedAt on hits."
    • changedInput schema / properties / cursor / description
      Previous value: -"Opaque cursor from previous nextCursor (GitHub Link page=)."New value: +"Opaque cursor from a previous nextCursor (GitHub Link page=). Not a bare page number."
    • changedInput schema / properties / direction / description
      Previous value: -"asc or desc (default desc)."New value: +"asc or desc (default desc). Echoed as data.direction."
    • changedInput schema / properties / limit / description
      Previous value: -"Max items to return. Default 30, max 100. Billed per result."New value: +"Max items to return (default 30, max 100). Billed per result."
    • changedInput schema / properties / sort / description
      Previous value: -"created|updated|pushed|full_name (default updated)."New value: +"created | updated | pushed | full_name (default updated). Not stars — GitHub's user-repos API has no stars sort. Echoed as data.sort."
    • changedInput schema / properties / type / description
      Previous value: -"owner|member|all (default owner)."New value: +"owner (default) | member | all — affiliation filter. Echoed as data.type."
    • changedInput schema / properties / username / description
      Previous value: -"GitHub username or profile URL."New value: +"GitHub username or profile URL, e.g. torvalds."
  3. Changed4 schema fields changed
    • changedInput schema / properties / cursor / description
      Previous value: -"Pagination cursor (page number as string). Leave empty for the first page; then pass the nextCursor value returned in the previous response."New value: +"Opaque cursor from previous nextCursor (GitHub Link page=)."
    • addedInput schema / properties / direction
      Added value: +{
+  "description": "asc or desc (default desc).",
+  "type": "string"
+}
    • addedInput schema / properties / sort
      Added value: +{
+  "description": "created|updated|pushed|full_name (default updated).",
+  "type": "string"
+}
    • addedInput schema / properties / type
      Added value: +{
+  "description": "owner|member|all (default owner).",
+  "type": "string"
+}
  4. Changed1 schema field changed
    • addedInput schema / properties / cursor
      Added value: +{
+  "description": "Pagination cursor (page number as string). Leave empty for the first page; then pass the nextCursor value returned in the previous response.",
+  "type": "string"
+}
  5. Changed1 schema field changed
    • changedInput schema / properties / cache / description
      Previous value: -"Responses are cached for 24 hours by default. Set false to bypass the cache and always fetch fresh data (default true)."New value: +"Set true to serve from the 24h response cache. Default false — always fetch fresh data."
  6. Changed1 schema field changed
    • addedInput schema / properties / cache
      Added value: +{
+  "description": "Responses are cached for 24 hours by default. Set false to bypass the cache and always fetch fresh data (default true).",
+  "type": "boolean"
+}
  7. Added

TDQS

A4.1/5.0
Behavior5/5

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

With no annotations present, the description carries the full burden and delivers: cost model ('~12 credits (0.4/result)'), billing policy ('Empty results and failures are never charged'), cache semantics ('cache=true for a free 24h cache hit (default always fresh)'), and opaque-cursor pagination. This far exceeds typical transparency for a read tool.

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?

Purpose is front-loaded in the first sentence, followed by cost, billing policy, and cache option — every sentence earns its place. A minor flaw: the per-item rate is stated twice ('~0.4/repo' and '0.4/result'), a small redundancy in an otherwise dense description.

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 7-parameter tool with no annotations and no output schema, the description covers the unusual operational aspects (cost, empty/failure billing, cache, cursor) while the schema covers all parameter semantics. The remaining gap is the response shape, partially mitigated by schema hints like 'from a previous nextCursor' and 'Echoed as data.sort'.

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 is unusually rich (defaults, option lists, the 'Not stars' caveat, 'Not a bare page number' cursor warning, 'Echoed as data.*'). The tool description only references sort/direction/type and cache=true at a high level, adding no incremental parameter meaning beyond the baseline.

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?

States a specific verb ('List') and a specific resource ('a user's repos'), with qualifying dimensions 'sort/direction/type'. The plural resource distinctly separates it from close siblings like github_repository (single repo) and github_trending_repositories (not user-scoped), so an agent can distinguish it without opening schemas.

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

Usage Guidelines3/5

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

The description gives clear operational context — caching, costs, cursor pagination — but never addresses when to pick this over alternatives. Among ~150 siblings, github_repository (singular) is an obvious alternative for one repo's details, yet no when/when-not or alternative routing is given; usage is only implied by the name and 'List a user's repos'.

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

All captapi toolsInspect
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.

Resources