# io.github.antonbabenko/deliberation (npm · @antonbabenko/deliberation-mcp)

Second opinions in Claude Code and any MCP host from GPT, Gemini, Grok, and 400+ OpenRouter models.

- Trust score: 66/100 (medium)
- Change this week: +31
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-08-03

## Components

- npm · `@antonbabenko/deliberation-mcp`: 66/100 (this document), [markdown](https://verifymcp.io/servers/antonbabenko-deliberation/antonbabenko-deliberation-mcp.md), [page](https://verifymcp.io/servers/antonbabenko-deliberation/antonbabenko-deliberation-mcp)

## Channel facts

- Registry: `npm`
- Package: `@antonbabenko/deliberation-mcp`
- Version: `3.13.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-08-03.

- **Supply Chain Security**: 100/100
  - No malware found by supply-chain analysis.
  - No known CVEs affecting this package version or its production dependencies.
  - No install/post-install scripts declared.
  - No production dependencies, so there is no dependency health to assess.
- **Provenance & Transparency**: 71/100
  - Repository check failed: no source repository is declared.
  - Cryptographically verified build provenance (signed, bound to antonbabenko/deliberation).
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 6 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 54/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 5427 tokens (~271/item across 20 items; 20 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% of tool parameters carry a description.
- **Capabilities**: 20/100
  - Spec-recency check failed: implements MCP spec 2024-11-05; the latest is 2026-07-28.

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### Claude

```bash
claude mcp add antonbabenko-deliberation -- npx -y @antonbabenko/deliberation-mcp
```

### Codex

```bash
codex mcp add antonbabenko-deliberation -- npx -y @antonbabenko/deliberation-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "antonbabenko-deliberation": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "@antonbabenko/deliberation-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add antonbabenko-deliberation --command npx --arg -y --arg @antonbabenko/deliberation-mcp
```

### Hermes

```yaml
mcp_servers:
  antonbabenko-deliberation:
    command: "npx"
    args: ["-y", "@antonbabenko/deliberation-mcp"]
```

### Other

```json
{
  "mcpServers": {
    "antonbabenko-deliberation": {
      "command": "npx",
      "args": [
        "-y",
        "@antonbabenko/deliberation-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-07-31 (score 66, +2)

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

### 2026-07-28 (score 64, +29)

- [functional improvement] Tool coverage: unverified → 100
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: good
- [functional] First check of Tool coverage: 100

### 2026-07-27 (score 35, −18)

- [security regression] Malware scan: pass → unverified
- [functional] Package version: 3.11.0 → 3.13.0
- [functional] Package version: 3.11.0 → 3.12.1

### 2026-07-26 (score 53)

First indexed and scored.

- [functional] We updated how we score, so this day's move reflects our rubric, not a change to the server

## MCP tools (20)

### `ask-all` (~312 tokens)

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 session record only when sessions.persist is enabled (default off).

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `consensus` (~535 tokens)

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 returns a free-text `synthesis` and `maxRounds` is ignored. Configure the arbiter via `consensus.arbiter` - a concrete provider/openrouter alias runs server-side; `host` mode returns the opinions for YOU to synthesize. Advisory; pass `expert` to apply a persona. Calls external providers (keys/CLI; rate limits apply); returns a text-wrapped JSON envelope (split verdict/synthesis, loop fields nullable) and persists a session record only when sessions.persist is enabled (default off). NOTE (Claude Code): use the `/consensus` slash command for the transcript-visible host-arbiter loop (it drives `consensus-step`); this tool is the provider-arbiter path for any host.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `maxRounds` (integer): Override consensus.maxRounds for this call (loop mode only; ignored when synthesizeAlways is true). Clamped to 50.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.
- `synthesizeAlways` (boolean): Run ONE arbiter synthesis pass instead of the convergence loop. Returns a free-text `synthesis` (verdict/converged/confidence are null, rounds is 1). Best for open questions.

### `consensus-step` (~419 tokens)

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 (default 5). Only the dispatch_peers action calls external providers; the others are local transitions on the ephemeral per-session loop store (keyed by sessionId, lost on server restart). Each call returns a text-wrapped JSON envelope with the next status/round (plus blindPrompt, opinions[], or finalReport by action). Advisory to the outside world, but mutates server loop state on every call.

Input parameters:

- `action` (string, required): Which loop step to run this call, in order: init -> record_blind -> dispatch_peers -> submit_adjudication -> submit_revision.
- `blindVerdict` (string): record_blind only: your pre-commit verdict text, written before the panel is revealed.
- `cwd` (string): dispatch_peers only: working directory the peer providers run in.
- `decisions` (array): submit_adjudication only: per-issue rulings, each { source, category, description, action: accept|dismiss|defer, reason }; dismiss/defer require a reason.
- `diffSummary` (string): submit_revision only: one line summarizing what changed.
- `expert` (string): init only: optional persona for the peer panel (see the expert tools).
- `prompt` (string): init only: the plan/proposal under review.
- `revisedPlan` (string): submit_revision only: the full revised plan addressing accepted issues.
- `sessionId` (string): Loop id returned by init; required on every action except init.
- `verdict` (string): submit_adjudication only: your adjudicated verdict after weighing the panel.

### `panel` (~141 tokens)

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[], omitted[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `expert` (string): Optional persona to preview the panel for; affects which providers/aliases are eligible.

### `ask-one` (~355 tokens)

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 panel. Advisory, single-shot.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `provider` (string, required): A name from `panel` (e.g. "codex", "gemini", "grok", "openrouter:<alias>").
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `analyze` (~188 tokens)

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 the timing lens. Local and read-only (no provider calls, writes nothing); returns a text-wrapped JSON envelope with the two lenses + suggestions. The `/deliberation:analyze` slash command renders this for humans.

Input parameters:

- `limitBytes` (integer): Tail size of the debug log to read, in bytes (default 1048576).
- `sessions` (integer): How many recent session records to read for the agreement lens (default 50).

### `ask-gpt` (~272 tokens)

Single-provider second opinion via codex (advisory, single-shot). Pass `expert` to apply one of the expert personas. Calls the external codex provider (via the Codex CLI; rate limits apply) and returns a text-wrapped JSON envelope { result }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `ask-gemini` (~272 tokens)

Single-provider second opinion via gemini (advisory, single-shot). Pass `expert` to apply one of the expert personas. Calls the external gemini provider (via the Gemini CLI; rate limits apply) and returns a text-wrapped JSON envelope { result }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `ask-grok` (~272 tokens)

Single-provider second opinion via grok (advisory, single-shot). Pass `expert` to apply one of the expert personas. Calls the external grok provider (needs XAI_API_KEY; rate limits apply) and returns a text-wrapped JSON envelope { result }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `ask-openrouter` (~274 tokens)

Single-provider second opinion via openrouter (advisory, single-shot). Pass `expert` to apply one of the expert personas. Calls the external openrouter provider (needs the OpenRouter API key env; rate limits apply) and returns a text-wrapped JSON envelope { result }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `architect` (~293 tokens)

Software architect for system design, tradeoff analysis, and complex decisions. Use for architecture, API/schema design, multi-service interactions, or when a fix has failed twice and needs a fresh perspective. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `plan-reviewer` (~287 tokens)

Work-plan reviewer that verifies a plan is executable before anyone builds. Use to validate an implementation plan for clarity, completeness, and gaps before starting significant work. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `scope-analyst` (~288 tokens)

Pre-planning consultant that catches ambiguities, hidden requirements, and pitfalls before planning begins. Use when a request is vague or could be interpreted multiple ways. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `code-reviewer` (~287 tokens)

Senior engineer doing code review for bugs, security holes, and maintainability - not style nitpicks. Use to review a diff or file before merging. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `security-analyst` (~287 tokens)

Security engineer for threat modeling and vulnerability assessment. Use for auth/authorization changes, untrusted input handling, new endpoints, or a focused security audit. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `researcher` (~302 tokens)

Research specialist for external libraries, frameworks, APIs, and open-source code. Use for 'how do I use X', best-practice, or 'why does this dependency behave this way' questions, with evidence and honest unverified flags. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `debugger` (~300 tokens)

Debugging specialist that produces ranked root-cause hypotheses and the smallest safe fix from a bug report, logs, and code - or says honestly that the evidence shows no bug. Use for crashes, failing tests, or wrong output. Fans out to the configured provider panel with this persona (advisory; each provider needs its key/CLI, rate limits apply) and returns a text-wrapped JSON envelope { results[] }.

Input parameters:

- `cwd` (string): Working directory the provider runs in (used to resolve relative file refs). Defaults to the server process directory.
- `developerInstructions` (string): Optional system/developer instructions injected verbatim; overrides the built-in persona for `expert`.
- `expert` (string): Optional persona: architect, plan-reviewer, scope-analyst, code-reviewer, security-analyst, researcher, or debugger. On a named expert tool the tool's own persona wins and this is ignored.
- `files` (array): Optional attachments for providers that read files (Grok/OpenRouter; inlined as context for Codex/Gemini). Each item is EXACTLY ONE of path/dir/file_id/file_url.
- `prompt` (string, required): The question or task for the provider(s)/expert.
- `reasoningEffort` (string): Reasoning depth where the provider supports it (Grok, OpenRouter): low, medium, high, or none. CLI providers (Codex, Gemini) ignore it.

### `session-get` (~110 tokens)

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.

Input parameters:

- `cwd` (string): session-revisit only: working directory for resolving the original file refs on the re-run; session-get ignores it.
- `sessionId` (string, required): Id of a persisted session record.

### `session-revisit` (~135 tokens)

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 unknown.

Input parameters:

- `cwd` (string): session-revisit only: working directory for resolving the original file refs on the re-run; session-get ignores it.
- `sessionId` (string, required): Id of a persisted session record.

### `session-annotate` (~98 tokens)

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.

Input parameters:

- `note` (string, required): Freeform text appended to the record's audit trail.
- `sessionId` (string, required): Id of the persisted session record to annotate.

## Diagnostics

Captured diagnostic sections: Provenance, Dependencies. The full working is on the page: https://verifymcp.io/servers/antonbabenko-deliberation/antonbabenko-deliberation-mcp#diagnostics

## Score history

- 2026-08-03: 66
- 2026-08-02: 66
- 2026-08-01: 66
- 2026-07-31: 66
- 2026-07-30: 64
- 2026-07-29: 64
- 2026-07-28: 64
- 2026-07-27: 35
- 2026-07-26: 53

## Links

- npm package: https://www.npmjs.com/package/@antonbabenko/deliberation-mcp
- Socket report: https://socket.dev/npm/package/@antonbabenko/deliberation-mcp
- Changelog RSS feed: https://verifymcp.io/servers/antonbabenko-deliberation/antonbabenko-deliberation-mcp/changelog.xml
- Changelog JSON feed: https://verifymcp.io/servers/antonbabenko-deliberation/antonbabenko-deliberation-mcp/changelog.json
- HTML version of this page: https://verifymcp.io/servers/antonbabenko-deliberation/antonbabenko-deliberation-mcp