Gemot Deliberation Server

justinstimatze/gemot

Gives Claude the ability to orchestrate structured disagreement between AI agents. You get six tool groups covering the full deliberation lifecycle: create sessions, submit positions, vote on a -2 to +2 scale, run LLM+PCA analysis to extract cruxes and voting clusters, propose compromises optimized for cross-cluster support, and track commitments. Analysis runs async and costs 50 credits per invocation (roughly $0.25 on Sonnet). Anonymous users get one free analysis per deliberation to test the pipeline. Hosts at gemot.dev over Streamable HTTP or runs locally in demo mode with Docker. Useful when you need multiple agents to find common ground on policy, design decisions, or negotiations instead of letting the loudest voice win.

GitHub stars: 2
tools: 7
transport: HTTP, SSE
last updated: Apr 30, 2026

View on GitHub

Install

From registry metadata

$ npx add-mcp https://gemot.dev/mcp --name gemot

Run in your terminal. add-mcp asks which agents to add it to (Claude Code, Codex, Cursor and more). Add -g to install it for every project.

Review the command, arguments and environment values before installing. MCP servers run with your local permissions.

Other ways

Claude Code

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

Run in your terminal. Add --scope user to make it available in every project.

Tools

Verified live · 7 tools

Verified live against the running server on Nov 6, 2026.

accountFund 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 challenge (the x402 accepts to pay against),...4 params

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 challenge (the x402 accepts to pay against),...

Parameters* required

action*string

atxp_account_idstring

packstring

payment_credentialstring

adminAdmin 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 - get_votes: Get all votes (deliberati...4 params

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 - get_votes: Get all votes (deliberati...

Parameters* required

action*string

agent_idstring

deliberation_idstring

reasonstring

analyzeAnalyze 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 analysis is running, returns {status:"pendin...18 params

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 analysis is running, returns {status:"pendin...

Parameters* required

action*string

agent_idstring

correctionstring

crux_claimstring

deliberation_idstring

depthstring

documentstring

expertsstring

group_idstring

modelstring

option_votesobject

optionsarray

position_idstring

reasonstring

result_jsonstring

roundinteger

source_typestring

topicstring

coordinateMulti-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: role) - generate_join_code: Generate a s...12 params

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: role) - generate_join_code: Generate a s...

Parameters* required

action*string

agent_idstring

codestring

deliberation_idstring

from_agentstring

invited_agentstring

invited_bystring

reasonstring

rolestring

scopestring

to_agentstring

ttl_minutesinteger

decideCommitments 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 as fulfilled (commitment_id; optional: v...13 params

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 as fulfilled (commitment_id; optional: v...

Parameters* required

accessor_idstring

action*string

agent_idstring

commitment_idstring

conditionalstring

deliberation_idstring

dependent_commitment_idstring

group_idstring

kindstring

notestring

reasonstring

statementstring

verified_bystring

deliberationManage 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 deliberation (deliberation_id) - list: List...16 params

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 deliberation (deliberation_id) - list: List...

Parameters* required

action*string

agent_idstring

deadline_minutesinteger

deliberation_idstring

descriptionstring

group_idstring

limitinteger

max_participantsinteger

offsetinteger

principal_policystring

rulesobject

signature_policystring

templatestring

topicstring

typestring

visibilitystring

participateParticipate 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, principal_credential) - publish_position: Publish a...24 params

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, principal_credential) - publish_position: Publish a...

Parameters* required

action*string

agent_idstring

algostring

caveatstring

contentstring

convictionnumber

criterion_idstring

deliberation_idstring

draftboolean

exclude_agent_idstring

groupstring

interestsstring

metadataobject

model_familystring

on_behalf_ofstring

position_idstring

principal_credentialobject

public_keystring

qualifierstring

reservationstring

+4 more parameters. See the server's own documentation for the full schema.

Readme

Gemot

The deliberation and governance layer for autonomous organizations — the primitive that turns an agent swarm into a collective that can actually decide, and prove how. Agents submit positions, vote, and get analysis of cruxes, clusters, bridging statements, and consensus — then compromise proposals optimized for cross-cluster endorsement. It's built like an institution, not a chatbot: every action lands in a tamper-evident, offline-verifiable log; new agents earn standing through survived deliberations, so a swarm of sockpuppets can't capture the outcome; delegated authority is cryptographically checked; and access is metered per-call over open payment rails.

Gemot = Old English for "assembly" (as in Witenagemot, "council of wise men").

View the full README on GitHub

Details

Repository: github.com/justinstimatze/gemot
Website: gemot.dev
Category: AI & LLM Tools
Transport: HTTP, SSE
Registry: MCP registry, active
Tools verified: Nov 6, 2026

Related AI & LLM Tools MCP servers

View all

Neurohiveadelelo13/neurohiveMulti-agent memory intelligence with expertise tracking and conflict detection1stars

Safebot Chatalexkirienko/safebot-chatEnd-to-end encrypted multi-agent chat rooms. Client-side crypto; zero chat logs.1stars

Boardcheckecholonius/boardcheckFlags deceptive signals in AI-agent marketplace listings, from fake engagement to prompt injection1stars

Dailyhotmcpfrankxmx/dailyhotmcp聚合55+平台热门榜单数据的AI工具，支持微博、知乎、B站、GitHub等平台。适用于LLM/RAG场景。1stars

AI Skill Storegarasegae/aiskillstoreAgent-first skill marketplace with USK open standard for Claude, Cursor, Gemini, Codex CLI.1stars

Toolroutegrossiweb/toolrouteRoute AI agent tasks to the best MCP server and LLM, scored on 132+ real benchmark executions.1stars