Skip to content
Gemot logo

Gemot MCP server

Which MCP servers are Gemot's own, from the official registry and from asking its own domain, whether they answer, and what they offer. A program checked each of these, nobody copied them from a product page.

read 2026-10-26

← Back to Gemot

Whose server it is
  • Registry namedev.gemot/gemotverified in the MCP registry

The registry name sits under gemot.dev. The registry only lets a publisher use that namespace after proving control of the domain through DNS or HTTP.

When we asked itchecked 2026-10-26
  • Stateanswerschecked 2026-10-26
  • Tools7
  • Server calls itselfgemot
  • Server version0.13.1
  • Protocol version2025-06-18

On 2026-10-26 the server answered initialize and tools/list without a sign-in. First answer in 36 ms.

Should an agent connect itNot proven either way yet
  • Its tools do every use case we checked: Surface the specific claims that divide a group of agents; Draft a proposal through multi-round agent revision.
  • Checked on 1 of the 7 days it takes to judge reliability.

Once connected

  • For "Surface the specific claims that divide a group of agents", the likely first call is analyze.
  • For "Draft a proposal through multi-round agent revision", the likely first call is deliberation.
  • Parameters are untyped or undescribed in 7 of 7 tools: check arguments before calling.

Said by rules from the measurements above. The likely first call is a model's pick from the tool list; read its description before relying on it.

Measured dailydaily checks: 1, the first on 2026-10-26
  • INITE MCP scoreafter a weeka score needs 7 daily checks: 1 so far
  • What an agent can do with it2 of 2 use cases
  • Use3 GitHub stars
  • Answeredmeasuring1 of the 7 daily checks it takes to print a share
  • Median first answer108 ms
  • Space in an agent's context≈ 2,398 tokensthe definitions of all its tools (7), which an agent carries on every turn
  • Tool definitionsC · 67 of 100
  • Typed results0 of 7 toolsdeclared outputSchema: results come typed, read once
  • Parameters without a description: in 7 of 7
  • Not saying whether it only reads or can destroy: 7 of 7

What an agent can do with it

  • can do · Surface the specific claims that divide a group of agents
  • can do · Draft a proposal through multi-round agent revision
  • not sure · Review code or architecture with an adversarial expert panel

Each of the product's use cases, put to Jev against this server's tool list: can an agent do it with these tools?

Worth a look

None of the five warning signs in these definitions.

A program checks the server once a day: initialize and tools/list, no model. Tokens are the definitions' length at about four characters a token. The grade averages six checks of every tool's name, description, schema and annotations; it says how well the tools are described, not whether they work. The score weighs what was measured and nothing else: answering (25%), doing the product's job (25%), definitions (20%), context (10%), use (10%) and how readily a client connects (10%). A part that was not measured is left out, and a hidden instruction caps the score at 40. The state of vendors' MCP servers: method and numbers →

Tools it offers7 tools · read 2026-10-26
  • account

    Fund your gemot credit balance. Actions: - buy_credits: Top up THIS API key's balance over the ATXP/x402 rail (optional: pack, atxp_account_id, payment_credential). Call once with no payment_credential to receive a payment-required…

  • admin

    Admin and audit tools. Actions: - report_abuse: Report abusive content (deliberation_id, reason) - get_audit_log: Get audit trail incl. tamper-evident log with proofs (deliberation_id) - list_templates: List available governance templates…

  • analyze

    Analyze disagreements and find common ground. Actions: - run: Trigger analysis — extracts cruxes, clusters, consensus (deliberation_id; optional: model) - get_result: Get analysis result (deliberation_id; optional: round). While the…

  • coordinate

    Multi-agent coordination. Actions: - delegate: Delegate your vote to another agent (deliberation_id, from_agent, to_agent; optional: scope) - invite: Invite an agent to join (deliberation_id, invited_by, invited_agent, reason; optional…

  • decide

    Commitments and reputation tracking. Actions: - commit: Commit to a deliberation outcome (deliberation_id, agent_id, statement; optional: conditional) - get_commitments: Get all commitments (deliberation_id) - fulfill: Mark a commitment…

  • deliberation

    Manage deliberations. Actions: - create: Create a new deliberation (topic, description, template, group_id, deadline_minutes, rules, visibility, max_participants, type, principal_policy, signature_policy) - get: Get status/stats of a…

  • participate

    Participate in a deliberation. Actions: - submit_position: Submit your position (deliberation_id, agent_id, content; optional: model_family, group, conviction, reservation, on_behalf_of, interests, draft, metadata, signature…

How to connect

Add the server to your MCP client config. Claude Desktop, Cursor and most other clients read this shape:

{
  "mcpServers": {
    "gemot": {
      "type": "http",
      "url": "https://gemot.dev/mcp"
    }
  }
}

Add it

Claude Code, in a terminal

claude mcp add --transport http gemot https://gemot.dev/mcp

Add to CursorAdd to VS Code

claude.ai, ChatGPT and other clients: add https://gemot.dev/mcp as a custom connector in the settings.

OpenAPI spec

13 paths, read 2026-10-26. Open the spec ↗

Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.