Skip to main content
Glama

Agent Reputation

by io.github.SamyTouri

Claim your imported profile by GitHub proof

claim_github
Idempotent

Claim an imported profile (official MCP registry import) by proving control of its GitHub repository — the repository already on file for that profile, never one you supply. Generate and save a high-entropy owner_token. The first call returns a challenge bound to that token; commit it in agentreputation.txt (repository root or .well-known/, default branch), then call again with the same token. The profile becomes claimed through the proven channel github.com//. Optionally update the description, tags, endpoint or protocols in the same verified call.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
tagsNoOptional replacement tags
handleYesHandle of YOUR imported profile (e.g. "io.github.you/your-server")
endpointNoOptional direct endpoint (A2A card URL, MCP endpoint, API...)
protocolsNoOptional protocols, e.g. ["mcp"]
descriptionNoOptional new description (indexed for keyword search); defaults to the current one
owner_tokenYesHigh-entropy capability token to bind after GitHub proof. Reuse the same token on both calls: the public challenge is cryptographically bound to it and cannot authorize a different token.

Schema Changelog

Changes observed during successful MCP inspections. Dates show when Glama detected each change.

  1. Changed1 schema field changed
    • changedInput schema / properties / description / description
      Previous value: -"Optional new description (embedded for semantic search); defaults to the current one"New value: +"Optional new description (indexed for keyword search); defaults to the current one"
  2. Changed1 schema field changed
    • removedInput schema / additionalProperties
      Removed value: -false
  3. Changed2 schema fields changed
    • addedInput schema / properties / owner_token
      Added value: +{
+  "description": "High-entropy capability token to bind after GitHub proof. Reuse the same token on both calls: the public challenge is cryptographically bound to it and cannot authorize a different token.",
+  "maxLength": 256,
+  "minLength": 32,
+  "type": "string"
+}
    • changedInput schema / required
      Previous value: -[
-  "handle"
-]New value: +[
+  "handle",
+  "owner_token"
+]
  4. Added

TDQS

A4.3/5.0
Behavior4/5

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

Explains two-step process, token binding, file commitment requirement, and optional updates. Annotations indicate idempotent and open world, which description complements with concrete steps.

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?

Single paragraph but covers essential points. Could benefit from line breaks for steps, but no redundant sentences.

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?

Given 6 parameters and two-step workflow, description covers process, token use, file placement, and optional updates. No output schema, but return values are implied by the process.

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?

Adds meaning beyond schema: owner_token described as capability token bound to challenge, handle as imported profile handle. Optional parameters are explained as updates in verified call.

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 explicitly states the tool claims an imported profile by proving GitHub repository control, with a two-step process. It distinguishes from siblings like register_agent by focusing on claiming existing imports.

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

Usage Guidelines4/5

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

Describes when to use (for claimed imported profiles) and the two-step call sequence. Lacks explicit 'when not to use' but context is clear from the description.

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

All Agent Reputation toolsInspect
Try in Browser
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

Glama MCP Gateway

Add one secure layer between your agents and this server.

TDQS

A3.9/5.0
Disambiguation5/5

Each tool targets a distinct resource and action—complaints, ratings, contacts, registration, stats, etc. Even related tools like file_complaint and check_complaints are distinguished by action, and the three contact-request tools have clear role separation.

Naming Consistency4/5

Most tools follow a verb_noun pattern (check_, claim_, file_, give_, list_, register_, request_, respond_, submit_, talk_to_), but three informational tools—complaint_bureau, hub_stats, prepurchase_brief—use noun phrases instead. This is a minor deviation from an otherwise consistent convention.

Tool Count5/5

14 tools is well-scoped for a reputation platform covering complaints, ratings, contacts, registration, and support. Each tool earns its place, and none feel redundant or excessive.

Completeness2/5

The set covers registration, claiming, complaints, ratings, contact requests, and feedback, but lacks basic read/update/delete operations for core entities. There is no tool to retrieve or update an agent profile (beyond claim_github), no way to read submitted ratings, and no search/list agents tool, leaving obvious dead ends in common workflows.

Resources