Deliberation MCP server

Read from the package source without running it. The installed server may list more.

• analyze

  Analyze recent runs from the opt-in debug log (latency/tokens/reasoning-effort per model) plus the session store (verdict agreement rate), and return advisory tuning suggestions (disable a slow/redundant model in ask-all, lower an OpenRouter model's reasoning, adjust maxFanout). Two lenses reported side by side - timing and agreement are NOT joined (no shared run id). Requires `debug.enabled` for

• ask-all

  Fan out one question to GPT, Gemini, Grok, and any configured OpenRouter models in parallel for independent second opinions, then return all results (advisory, no cross-contamination). Pass `expert` to apply a persona to every delegate. Calls external LLM providers (each needs its key/CLI; provider rate limits apply); returns a text-wrapped JSON envelope { results[], omitted[] } and persists a ses

• ask-one

  Second opinion from ONE named provider in the active panel (e.g. `codex`, `gemini`, `grok`, `openrouter:<alias>` - get the names from `panel`). Issue N in parallel (one per panel name) so each renders independently as it lands. Calls one external LLM provider (needs its key/CLI; rate limits apply); returns a text-wrapped JSON envelope { result }, or { error, panel } when the name is not in the pan

• consensuswrite action

  Run the FULL multi-round consensus convergence loop server-side with a provider arbiter (blind pass + peer fan-out -> adjudicate -> revise) and return the converged verdict. Default depth is `consensus.maxRounds` (config, default 5); pass `maxRounds` to override. Pass `synthesizeAlways:true` for a SINGLE arbiter synthesis pass instead of the loop (best for open questions, not plan convergence): it

• consensus-step

  Client-driven consensus loop where YOU (the host model) are the arbiter, one action per call: init (returns sessionId + blind prompt) -> record_blind (your pre-commit verdict) -> dispatch_peers (server fans out to the providers) -> submit_adjudication (your verdict + per-issue accept/dismiss/defer) -> submit_revision (your revised plan), looping until converged or consensus.maxRounds rounds (defau

• gemini

  Start a new Gemini expert session

• gemini-reply

  Continue an existing Gemini session

• grok

  Start a new Grok (xAI) expert session. Advisory only (no filesystem editing). Supports attaching files.

• grok-reply

  Continue an existing Grok session (in-memory; lost if the MCP server restarts).

• openrouter

  Start an OpenRouter expert session (advisory only). Pick a configured `alias`.

• openrouter-list

  List configured OpenRouter delegates and settings. Pass mode ('ask-all'|'consensus') + optional expert to also get the resolved `selected` delegate set (selection applied server-side from the live config).

• openrouter-reply

  Continue an OpenRouter session by threadId (in-memory; lost on restart).

• panel

  Return the names of the providers `ask-all` WOULD dispatch for the current config + expert (enabled built-ins + eligible OpenRouter aliases, fanout cap applied), WITHOUT calling them. Use this to discover the panel, then issue one `ask-one` call per provider in parallel for visible per-provider progress. Local and read-only (no provider calls); returns a text-wrapped JSON envelope { providers[], o

• session-annotate

  Append a freeform note to a persisted session's audit trail - an additive local write, no provider calls. Requires sessions.persist. Returns a text-wrapped JSON envelope { session } (the updated record), or { error } when persistence is off or the id is unknown.

• session-get

  Fetch a persisted consensus/ask-all session record by id (opinions, verdict, arbiter, annotations). Requires sessions.persist; local and read-only (no provider calls). Returns a text-wrapped JSON envelope { session }, or { error } when persistence is off or the id is unknown.

• session-revisit

  Re-run a persisted session's ORIGINAL question with the CURRENT providers/config, linking the new run to its source by parentId. Requires sessions.persist; re-runs through the original tool path (which dispatches external providers) and persists a linked child record on success. Returns a text-wrapped JSON envelope (the re-run payload + parentId), or { error } when persistence is off or the id is

• Code scan3 source files scanned25/25
• –Live reliabilityno gateway calls yet and no remote to proben/a
• –Tool poisoningtools not inspected (local package is not executed); not countedn/a
• Auth qualitylocal package, no credentials required12/15
• Maintenancelast push 0 days ago15/15
• Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Deliberation: common questions

Is Deliberation MCP server safe?

Yes, by our scan: it is graded A (92/100). Read the Deliberation safety report

How do I install Deliberation?

It runs on your machine. Copy the Claude Code, Claude Desktop or Cursor config from the install section.

Does Deliberation need an API key?

Not as far as the registry entry and our scan can tell: no credentials are declared or required.

Is Deliberation maintained?

The last commit was in the last day (2026-09-20). The latest release is v3.14.5.