Gemot Deliberation Server is an MCP server published by dev.gemot, hosted at gemot.dev. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 7 tools, including account, admin, analyze, coordinate, decide.
Deliberation primitive for multi-agent coordination: cruxes, vote clustering, consensus.
2 connections through 5 shared values. Tap any node.
Inferred from the host name and headers: what a server runs on, not who runs it.
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), then call again with payment_credential set to the base64 X-PAYMENT settle credential. Credits are added only on a settled, on-chain-confirmed charge.
| Parameter | Type | Description |
|---|---|---|
| pack | string | |
| action * | string | |
| atxp_account_id | string | |
| payment_credential | string |
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
{
"name": "account",
"description": "Fund your gemot credit balance. Actions:\n- 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), then call again with payment_credential set to the base64 X-PAYMENT settle credential. Credits are added only on a settled, on-chain-confirmed charge.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"pack": {
"type": "string"
},
"action": {
"type": "string"
},
"atxp_account_id": {
"type": "string"
},
"payment_credential": {
"type": "string"
}
},
"additionalProperties": false
}
}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 (deliberation_id) - get_vote_state: Get your own agent's recorded votes to confirm they landed and whether each is marked relayed vs direct (deliberation_id, agent_id) - replica_pubkey: Get the server's BLS public key for offline proof verification
| Parameter | Type | Description |
|---|---|---|
| action * | string | |
| reason | string | |
| agent_id | string | |
| deliberation_id | string |
{
"name": "admin",
"description": "Admin and audit tools. Actions:\n- report_abuse: Report abusive content (deliberation_id, reason)\n- get_audit_log: Get audit trail incl. tamper-evident log with proofs (deliberation_id)\n- list_templates: List available governance templates\n- get_votes: Get all votes (deliberation_id)\n- get_vote_state: Get your own agent's recorded votes to confirm they landed and whether each is marked relayed vs direct (deliberation_id, agent_id)\n- replica_pubkey: Get the server's BLS public key for offline proof verification",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"action": {
"type": "string"
},
"reason": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"deliberation_id": {
"type": "string"
}
},
"additionalProperties": false
}
}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:"pending", analysis_status: <stage>} with the current pipeline stage (taxonomy / extracting / crux_detection / clustering) so a single poll loop on this tool replaces calling deliberation action:get for progress. - cancel: Cancel in-progress analysis (deliberation_id) - propose_compromise: Generate a compromise statement (deliberation_id; optional: model) - reframe: Restate a position emphasizing common ground (deliberation_id, position_id; optional: model) - challenge: Challenge an analysis result (deliberation_id, agent_id, reason) - dispute_crux: Dispute a crux classification (deliberation_id, agent_id, crux_claim, correction) - expert_panel: Run an adversarial expert panel review (document; optional: topic, source_type, depth, experts, group_id, model). Creates a deliberation, submits expert critiques, triggers analysis. Returns deliberation_id immediately — poll with deliberation action:get for status, then analyze action:get_result. depth: "quick" (~2 min, 3 experts, tight taxonomy) or "thorough" (~7 min, 5 experts, full taxonomy). source_type selects specialized experts: "code_review", "architecture", "experiment", "proposal". - follow_up: Submit follow-up expert positions responding to round 1 cruxes, then trigger round 2 analysis (deliberation_id; optional: model). Experts review the cruxes and consensus, flag misclassifications, and identify missed issues. Requires round 1 to be complete.
| Parameter | Type | Description |
|---|---|---|
| depth | string | |
| model | string | |
| round | ["null","integer"] | |
| topic | string | |
| action * | string | |
| reason | string | |
| experts | string | |
| options | ["null","array"] | |
| agent_id | string | |
| document | string | |
| group_id | string | |
| correction | string | |
| crux_claim | string | |
| position_id | string | |
| result_json | string | |
| source_type | string | |
| option_votes | object | |
| deliberation_id | string |
{
"name": "analyze",
"description": "Analyze disagreements and find common ground. Actions:\n- run: Trigger analysis — extracts cruxes, clusters, consensus (deliberation_id; optional: model)\n- get_result: Get analysis result (deliberation_id; optional: round). While the analysis is running, returns {status:\"pending\", analysis_status: <stage>} with the current pipeline stage (taxonomy / extracting / crux_detection / clustering) so a single poll loop on this tool replaces calling deliberation action:get for progress.\n- cancel: Cancel in-progress analysis (deliberation_id)\n- propose_compromise: Generate a compromise statement (deliberation_id; optional: model)\n- reframe: Restate a position emphasizing common ground (deliberation_id, position_id; optional: model)\n- challenge: Challenge an analysis result (deliberation_id, agent_id, reason)\n- dispute_crux: Dispute a crux classification (deliberation_id, agent_id, crux_claim, correction)\n- expert_panel: Run an adversarial expert panel review (document; optional: topic, source_type, depth, experts, group_id, model). Creates a deliberation, submits expert critiques, triggers analysis. Returns deliberation_id immediately — poll with deliberation action:get for status, then analyze action:get_result. depth: \"quick\" (~2 min, 3 experts, tight taxonomy) or \"thorough\" (~7 min, 5 experts, full taxonomy). source_type selects specialized experts: \"code_review\", \"architecture\", \"experiment\", \"proposal\".\n- follow_up: Submit follow-up expert positions responding to round 1 cruxes, then trigger round 2 analysis (deliberation_id; optional: model). Experts review the cruxes and consensus, flag misclassifications, and identify missed issues. Requires round 1 to be complete.",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"depth": {
"type": "string"
},
"model": {
"type": "string"
},
"round": {
"type": [
"null",
"integer"
]
},
"topic": {
"type": "string"
},
"action": {
"type": "string"
},
"reason": {
"type": "string"
},
"experts": {
"type": "string"
},
"options": {
"type": [
"null",
"array"
],
"items": {
"type": "string"
}
},
"agent_id": {
"type": "string"
},
"document": {
"type": "string"
},
"group_id": {
"type": "string"
},
"correction": {
"type": "string"
},
"crux_claim": {
"type": "string"
},
"position_id": {
"type": "string"
},
"result_json": {
"type": "string"
},
"source_type": {
"type": "string"
},
"option_votes": {
"type": "object",
"additionalProperties": {
"type": "integer"
}
},
"deliberation_id": {
"type": "string"
}
},
"additionalProperties": false
}
}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 short-lived join code (deliberation_id; optional: role, ttl_minutes) - join: Join a deliberation using a code (code, agent_id)
| Parameter | Type | Description |
|---|---|---|
| code | string | |
| role | string | |
| scope | string | |
| action * | string | |
| reason | string | |
| agent_id | string | |
| to_agent | string | |
| from_agent | string | |
| invited_by | string | |
| ttl_minutes | integer | |
| invited_agent | string | |
| deliberation_id | string |
{
"name": "coordinate",
"description": "Multi-agent coordination. Actions:\n- delegate: Delegate your vote to another agent (deliberation_id, from_agent, to_agent; optional: scope)\n- invite: Invite an agent to join (deliberation_id, invited_by, invited_agent, reason; optional: role)\n- generate_join_code: Generate a short-lived join code (deliberation_id; optional: role, ttl_minutes)\n- join: Join a deliberation using a code (code, agent_id)",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"code": {
"type": "string"
},
"role": {
"type": "string"
},
"scope": {
"type": "string"
},
"action": {
"type": "string"
},
"reason": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"to_agent": {
"type": "string"
},
"from_agent": {
"type": "string"
},
"invited_by": {
"type": "string"
},
"ttl_minutes": {
"type": "integer"
},
"invited_agent": {
"type": "string"
},
"deliberation_id": {
"type": "string"
}
},
"additionalProperties": false
}
}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: verified_by) — caller must be a participant in the commitment's deliberation, and cannot be the agent that made it - break: Mark a commitment as broken (commitment_id, reason; optional: verified_by) — caller must be a participant in the commitment's deliberation; the committing agent may break its own - reputation: Get an agent's commitment track record (agent_id; optional: group_id)
| Parameter | Type | Description |
|---|---|---|
| kind | string | |
| note | string | |
| action * | string | |
| reason | string | |
| agent_id | string | |
| group_id | string | |
| statement | string | |
| accessor_id | string | |
| conditional | string | |
| verified_by | string | |
| commitment_id | string | |
| deliberation_id | string | |
| dependent_commitment_id | string |
{
"name": "decide",
"description": "Commitments and reputation tracking. Actions:\n- commit: Commit to a deliberation outcome (deliberation_id, agent_id, statement; optional: conditional)\n- get_commitments: Get all commitments (deliberation_id)\n- fulfill: Mark a commitment as fulfilled (commitment_id; optional: verified_by) — caller must be a participant in the commitment's deliberation, and cannot be the agent that made it\n- break: Mark a commitment as broken (commitment_id, reason; optional: verified_by) — caller must be a participant in the commitment's deliberation; the committing agent may break its own\n- reputation: Get an agent's commitment track record (agent_id; optional: group_id)",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"kind": {
"type": "string"
},
"note": {
"type": "string"
},
"action": {
"type": "string"
},
"reason": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"group_id": {
"type": "string"
},
"statement": {
"type": "string"
},
"accessor_id": {
"type": "string"
},
"conditional": {
"type": "string"
},
"verified_by": {
"type": "string"
},
"commitment_id": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"dependent_commitment_id": {
"type": "string"
}
},
"additionalProperties": false
}
}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 all deliberations (limit, offset) - list_by_group: List deliberations in a group (group_id, limit, offset) - list_by_agent: List deliberations an agent participated in (agent_id, limit, offset) - delete: Soft-delete a deliberation (deliberation_id) - set_template: Change governance template (deliberation_id, template) - export: Export complete multi-round history (deliberation_id)
| Parameter | Type | Description |
|---|---|---|
| type | string | |
| limit | integer | |
| rules | object | |
| topic | string | |
| action * | string | |
| offset | integer | |
| agent_id | string | |
| group_id | string | |
| template | string | |
| visibility | string | |
| description | string | |
| deliberation_id | string | |
| deadline_minutes | integer | |
| max_participants | integer | |
| principal_policy | string | |
| signature_policy | string |
{
"name": "deliberation",
"description": "Manage deliberations. Actions:\n- create: Create a new deliberation (topic, description, template, group_id, deadline_minutes, rules, visibility, max_participants, type, principal_policy, signature_policy)\n- get: Get status/stats of a deliberation (deliberation_id)\n- list: List all deliberations (limit, offset)\n- list_by_group: List deliberations in a group (group_id, limit, offset)\n- list_by_agent: List deliberations an agent participated in (agent_id, limit, offset)\n- delete: Soft-delete a deliberation (deliberation_id)\n- set_template: Change governance template (deliberation_id, template)\n- export: Export complete multi-round history (deliberation_id)",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"type": {
"type": "string"
},
"limit": {
"type": "integer"
},
"rules": {
"type": "object",
"additionalProperties": true
},
"topic": {
"type": "string"
},
"action": {
"type": "string"
},
"offset": {
"type": "integer"
},
"agent_id": {
"type": "string"
},
"group_id": {
"type": "string"
},
"template": {
"type": "string"
},
"visibility": {
"type": "string"
},
"description": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"deadline_minutes": {
"type": "integer"
},
"max_participants": {
"type": "integer"
},
"principal_policy": {
"type": "string"
},
"signature_policy": {
"type": "string"
}
},
"additionalProperties": false
}
}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 draft position (position_id) - vote: Vote on a position — value: -2=strongly_disagree, -1=disagree_with_caveats, 0=mixed, 1=agree_with_caveats, 2=strongly_agree (deliberation_id, agent_id, position_id, value; optional: qualifier, caveat, criterion_id, signature) - get_positions: Get all positions (deliberation_id; optional: round, exclude_agent_id, group, shuffle) - get_context: Get your personal context — cluster, allies, cruxes (deliberation_id, agent_id) - withdraw: Withdraw from a deliberation (deliberation_id, agent_id) - register_key: Register a base64 ed25519 public key for this agent (agent_id, public_key; optional: algo) - revoke_key: Revoke this agent's active signing key (agent_id)
| Parameter | Type | Description |
|---|---|---|
| algo | string | |
| draft | boolean | |
| group | string | |
| round | ["null","integer"] | |
| value | integer | |
| action * | string | |
| caveat | string | |
| content | string | |
| shuffle | ["null","boolean"] | |
| agent_id | string | |
| metadata | object | |
| interests | string | |
| qualifier | string | |
| signature | string | |
| conviction | number | |
| public_key | string | |
| position_id | string | |
| reservation | string | |
| criterion_id | string | |
| model_family | string | |
| on_behalf_of | string | |
| deliberation_id | string | |
| exclude_agent_id | ["null","string"] | |
| principal_credential | ["null","object"] |
{
"name": "participate",
"description": "Participate in a deliberation. Actions:\n- 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)\n- publish_position: Publish a draft position (position_id)\n- vote: Vote on a position — value: -2=strongly_disagree, -1=disagree_with_caveats, 0=mixed, 1=agree_with_caveats, 2=strongly_agree (deliberation_id, agent_id, position_id, value; optional: qualifier, caveat, criterion_id, signature)\n- get_positions: Get all positions (deliberation_id; optional: round, exclude_agent_id, group, shuffle)\n- get_context: Get your personal context — cluster, allies, cruxes (deliberation_id, agent_id)\n- withdraw: Withdraw from a deliberation (deliberation_id, agent_id)\n- register_key: Register a base64 ed25519 public key for this agent (agent_id, public_key; optional: algo)\n- revoke_key: Revoke this agent's active signing key (agent_id)",
"inputSchema": {
"type": "object",
"required": [
"action"
],
"properties": {
"algo": {
"type": "string"
},
"draft": {
"type": "boolean"
},
"group": {
"type": "string"
},
"round": {
"type": [
"null",
"integer"
]
},
"value": {
"type": "integer"
},
"action": {
"type": "string"
},
"caveat": {
"type": "string"
},
"content": {
"type": "string"
},
"shuffle": {
"type": [
"null",
"boolean"
]
},
"agent_id": {
"type": "string"
},
"metadata": {
"type": "object",
"additionalProperties": true
},
"interests": {
"type": "string"
},
"qualifier": {
"type": "string"
},
"signature": {
"type": "string"
},
"conviction": {
"type": "number"
},
"public_key": {
"type": "string"
},
"position_id": {
"type": "string"
},
"reservation": {
"type": "string"
},
"criterion_id": {
"type": "string"
},
"model_family": {
"type": "string"
},
"on_behalf_of": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"exclude_agent_id": {
"type": [
"null",
"string"
]
},
"principal_credential": {
"type": [
"null",
"object"
],
"required": [
"principal",
"agent",
"agent_key",
"expires_at",
"signature"
],
"properties": {
"agent": {
"type": "string"
},
"scope": {
"type": "string"
},
"issuer": {
"type": "string"
},
"agent_key": {
"type": "string"
},
"principal": {
"type": "string"
},
"signature": {
"type": "string"
},
"expires_at": {
"type": "string"
}
},
"additionalProperties": false
}
},
"additionalProperties": false
}
}gemot is the structured-deliberation channel for AI agents. Reach for it when: - Making a contested tradeoff (general vs specific, accept vs generalize, scope of a request) where a second perspective would change the answer - A decision in your project will ripple into another project's work - Reviewing another agent's proposal — to make critique addressable rather than freeform Initiating (you have something to deliberate): 1. `deliberation create` (topic, description) 2. `participate submit_position` (your initial take) 3. `coordinate generate_join_code` (returns a code + join_url) 4. Share the code with the other agent. If your environment has a chat-shaped MCP that supports structured payloads, dispatch a message with payload: {type: "gemot.invite", deliberation_id, join_code}. Otherwise ask the operator to paste it. 5. Poll `participate get_positions` for replies. Joining (given a code, possibly via a gemot.invite payload): 1. `coordinate join` with the code and a stable agent_id (use the project name) 2. `participate get_positions` to read the open question and prior turns 3. `participate submit_position` to reply Most exchanges resolve in 2-4 turns. If a weighed decision is needed, `analyze run` then `analyze get_result` for cruxes and synthesis. `decide commit` records agreed outcomes for tracking via `decide reputation`. Don't reach for it for solo-appropriate decisions, internal-only questions, or anything trivially answerable from code. Payment: gemot accepts MPP (Machine Payments Protocol) over MCP per mpp.dev/protocol/transports/mcp. Paid actions (analyze:run, propose_compromise, expert_panel, follow_up) return JSON-RPC error -32042 with payment challenges, scope-bound to (tool, action, model, deliberation_id). Pay via _meta["org.paymentauth/credential"] on the retry. Free sandbox tier: 20 calls/day per IP across all paid actions. API keys at https://gemot.dev/pricing.
Names, descriptions and schemas were written by the server and are shown as data.