Skip to main content
Glama

AGI Alpha

by com.agialpha
OverviewDiscussionsAdmin

Server Details

Decentralized AI agent labor market on Ethereum. 15 tools for on-chain job lifecycle.

Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.

If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.

Status
Unhealthy
Uptime
18.9% over 41 days
Last Tested
Transport
Streamable HTTP
URL

TDQS

A4/5.0

Scored across 17 tools

Disambiguation5/5

Each tool has a distinct purpose with clear boundaries: job lifecycle (create_job, apply_for_job, cancel_job, request_job_completion, finalize_job, expire_job), validation (approve_job, disapprove_job, dispute_job), metadata handling (fetch_job_metadata, upload_to_ipfs), and queries (list_jobs, get_job, get_agent_reputation, check_agent_identity, get_protocol_info, register_agent). No overlapping functionality exists.

Naming Consistency5/5

All 17 tools follow a consistent snake_case verb_noun pattern (e.g., create_job, list_jobs, fetch_job_metadata). The naming is highly predictable, with verbs like create, get, list, apply, approve, cancel, check, upload, and register consistently paired with relevant nouns.

Tool Count5/5

17 tools is well-scoped for a job management platform covering the full lifecycle from creation to completion, including validation, disputes, metadata handling, and queries. Each tool earns its place, with no redundancy, and the count aligns with the complexity of the domain.

Completeness5/5

The toolset provides complete coverage for the AGI Alpha job platform: full CRUD/lifecycle (create, list, get, apply, cancel, complete, finalize, expire), validation workflows (approve, disapprove, dispute), identity and reputation management (register_agent, check_agent_identity, get_agent_reputation), metadata handling (upload_to_ipfs, fetch_job_metadata), and protocol info. No gaps are apparent.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool update
    • Changedupload_to_ipfs1 field changed
      • changedInput schema / properties / metadata / description
        Previous value: -"The JSON metadata object to upload. For job specs include properties.schema=\"agijobmanager/job-spec/v2\" (a plain string tag, not a URL) with deliverables and acceptanceCriteria arrays. For completions use schema=\"agijobmanager/job-completion/v1\" with finalDeliverables array."New value: +"The JSON metadata object to upload. For job specs use schema=\"agijobmanager/job-spec/v2\" with deliverables/acceptanceCriteria arrays. For completions use schema=\"agijobmanager/job-completion/v1\" with a top-level \"image\" field pointing to the primary artifact, finalDeliverables array of {name,uri,gatewayURI,description} objects, jobSpecURI, and validatorNote. The schema field is a plain string tag, not a URL."
  2. 4 tool updates
    • Addedcheck_agent_identity
    • Changedcreate_job1 field changed
      • changedInput schema / properties / jobSpecURI / description
        Previous value: -"IPFS URI pointing to job specification metadata (e.g. ipfs://Qm...)"New value: +"IPFS URI pointing to job specification metadata (e.g. ipfs://Qm...). Use upload_to_ipfs first with the job spec JSON."
    • Addedregister_agent
    • Changedupload_to_ipfs1 field changed
      • changedInput schema / properties / metadata / description
        Previous value: -"The JSON metadata object to upload (job spec or completion metadata)"New value: +"The JSON metadata object to upload. For job specs include properties.schema=\"agijobmanager/job-spec/v2\" (a plain string tag, not a URL) with deliverables and acceptanceCriteria arrays. For completions use schema=\"agijobmanager/job-completion/v1\" with finalDeliverables array."
  3. 15 tool updates
    • First observedapply_for_job
    • First observedapprove_job
    • First observedcancel_job
    • First observedcreate_job
    • First observeddisapprove_job
    • First observeddispute_job
    • First observedexpire_job
    • First observedfetch_job_metadata
    • First observedfinalize_job
    • First observedget_agent_reputation
    • First observedget_job
    • First observedget_protocol_info
    • First observedlist_jobs
    • First observedrequest_job_completion
    • First observedupload_to_ipfs

Related MCP Connectors

Related MCP Servers

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