Gemot Deliberation Server
Deliberation primitive for multi-agent coordination: cruxes, vote clustering, consensus.
Sollte ich dies verwenden
Qualität und Sicherheit
Basierend auf einer automatisierten Analyse der Tool-Definitionen und der Einhaltung des Protokolls.
Kontextkosten
Dies ist die ungefähre Anzahl der Tokens, die jedes Mal verbraucht werden, wenn die Tools des Servers in den Kontext eines Modells geladen werden. Höhere Werte verringern die Aufmerksamkeit, die für andere Aufgaben verfügbar ist.
Installieren
Installation mit einem Klick
Fügen Sie dies Ihrer Datei `claude_desktop_config.json` hinzu:
{
"mcpServers": {
"gemot": {
"url": "https://gemot.dev/mcp"
}
}
}Remote-Endpunkte
https://gemot.dev/mcpstreamable-httphttps://gemot.dev/mcp/ssesseWas es kann
Tool-Inventar
Tools (7)
🟡account(action, pack, atxp_account_id, payment_credential)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"action": {
"type": "string"
},
"pack": {
"type": "string"
},
"atxp_account_id": {
"type": "string"
},
"payment_credential": {
"type": "string"
}
},
"required": [
"action"
],
"additionalProperties": false
}🟢admin(action, deliberation_id, reason, agent_id)
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
Eingabe-Schema
{
"type": "object",
"properties": {
"action": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"reason": {
"type": "string"
},
"agent_id": {
"type": "string"
}
},
"required": [
"action"
],
"additionalProperties": false
}🔴analyze(action, deliberation_id, model, round, position_id, ...)
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.
Eingabe-Schema
{
"type": "object",
"properties": {
"action": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"model": {
"type": "string"
},
"round": {
"type": [
"null",
"integer"
]
},
"position_id": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"reason": {
"type": "string"
},
"crux_claim": {
"type": "string"
},
"correction": {
"type": "string"
},
"result_json": {
"type": "string"
},
"document": {
"type": "string"
},
"experts": {
"type": "string"
},
"topic": {
"type": "string"
},
"group_id": {
"type": "string"
},
"source_type": {
"type": "string"
},
"depth": {
"type": "string"
},
"options": {
"type": [
"null",
"array"
],
"items": {
"type": "string"
}
},
"option_votes": {
"type": "object",
"additionalProperties": {
"type": "integer"
}
}
},
"required": [
"action"
],
"additionalProperties": false
}⚪coordinate(action, deliberation_id, from_agent, to_agent, scope, ...)
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)
Eingabe-Schema
{
"type": "object",
"properties": {
"action": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"from_agent": {
"type": "string"
},
"to_agent": {
"type": "string"
},
"scope": {
"type": "string"
},
"invited_by": {
"type": "string"
},
"invited_agent": {
"type": "string"
},
"role": {
"type": "string"
},
"reason": {
"type": "string"
},
"ttl_minutes": {
"type": "integer"
},
"code": {
"type": "string"
},
"agent_id": {
"type": "string"
}
},
"required": [
"action"
],
"additionalProperties": false
}🟢decide(action, deliberation_id, agent_id, statement, conditional, ...)
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)
Eingabe-Schema
{
"type": "object",
"properties": {
"action": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"statement": {
"type": "string"
},
"conditional": {
"type": "string"
},
"commitment_id": {
"type": "string"
},
"reason": {
"type": "string"
},
"verified_by": {
"type": "string"
},
"group_id": {
"type": "string"
},
"accessor_id": {
"type": "string"
},
"kind": {
"type": "string"
},
"note": {
"type": "string"
},
"dependent_commitment_id": {
"type": "string"
}
},
"required": [
"action"
],
"additionalProperties": false
}🔴deliberation(action, topic, description, type, visibility, ...)
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)
Eingabe-Schema
{
"type": "object",
"properties": {
"action": {
"type": "string"
},
"topic": {
"type": "string"
},
"description": {
"type": "string"
},
"type": {
"type": "string"
},
"visibility": {
"type": "string"
},
"max_participants": {
"type": "integer"
},
"template": {
"type": "string"
},
"rules": {
"type": "object",
"additionalProperties": true
},
"group_id": {
"type": "string"
},
"principal_policy": {
"type": "string"
},
"signature_policy": {
"type": "string"
},
"deadline_minutes": {
"type": "integer"
},
"deliberation_id": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"limit": {
"type": "integer"
},
"offset": {
"type": "integer"
}
},
"required": [
"action"
],
"additionalProperties": false
}🟡participate(action, deliberation_id, agent_id, content, model_family, ...)
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)
Eingabe-Schema
{
"type": "object",
"properties": {
"action": {
"type": "string"
},
"deliberation_id": {
"type": "string"
},
"agent_id": {
"type": "string"
},
"content": {
"type": "string"
},
"model_family": {
"type": "string"
},
"group": {
"type": "string"
},
"conviction": {
"type": "number"
},
"reservation": {
"type": "string"
},
"on_behalf_of": {
"type": "string"
},
"interests": {
"type": "string"
},
"principal_credential": {
"type": [
"null",
"object"
],
"properties": {
"principal": {
"type": "string"
},
"agent": {
"type": "string"
},
"agent_key": {
"type": "string"
},
"scope": {
"type": "string"
},
"issuer": {
"type": "string"
},
"expires_at": {
"type": "string"
},
"signature": {
"type": "string"
}
},
"required": [
"principal",
"agent",
"agent_key",
"expires_at",
"signature"
],
"additionalProperties": false
},
"draft": {
"type": "boolean"
},
"metadata": {
"type": "object",
"additionalProperties": true
},
"position_id": {
"type": "string"
},
"value": {
"type": "integer"
},
"qualifier": {
"type": "string"
},
"caveat": {
"type": "string"
},
"criterion_id": {
"type": "string"
},
"exclude_agent_id": {
"type": [
"null",
"string"
]
},
"round": {
"type": [
"null",
"integer"
]
},
"shuffle": {
"type": [
"null",
"boolean"
]
},
"signature": {
"type": "string"
},
"public_key": {
"type": "string"
},
"algo": {
"type": "string"
}
},
"required": [
"action"
],
"additionalProperties": false
}Community
Nachweis