# the-high-council Several models from different labs plan in a blind proposal, debate and review loop. Your own keys. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the package rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 0.8.2 - **Author:** io.github.muad-yasin - **License:** MIT - **npm:** the-high-council - **Source:** https://github.com/muad-yasin/the-high-council-mcp - **Compatible clients:** claude-code, cursor, copilot, gemini (basis: transport) ## Trust 60/100 (B), scored on the package rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: not run - Obfuscation scan: not run - Evidence age: 9 days ## Security scan - **Status:** clean - **Scanned:** 2026-10-03T12:29:30.449Z - **Version scanned:** 0.8.0 - **CVEs:** none found by OSV at scan time ## Tools 16 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `my-first-chain` — A minimal real chain: one builder, one critic, one round. - `list_chains` — Chains available to run, with their description and worst-case price from a dry run. - `dry_run` — Price a chain without calling any model. chain is a chain name as list_chains shows it, never a path. json: true returns one JSON document instead of text: the - `start_run` — Start a harness run in the background. Returns the run id to poll with run_status, or started:false with the exit code and log tail if the run stopped at once. - `external_prompt` — When a run is paused at an external seat: the exact system and user prompt that stage needs answered. A run can wait on several stages at once (e.g. a panel of - `prepare_stage_prompt` — For a run paused at an external seat: write stage_prompt.md, a self-contained bundle a fresh subagent can act on with zero prior context, so a driving session c - `submit_stage` — Write the answer for an external stage into the run folder, then resume the run in the background. The stage must be one external_prompt lists under `waiting`; - `resume_run` — Resume a paused run after its external stage was answered (submit_stage does this for you), or a run stopped by the spend cap (pass a higher max_usd). Completed - `spend_report` — What every run has cost across a window of days, not just one run. Derived from the run folders on disk - nothing is recorded anywhere else and nothing leaves t - `verdict_stats` - `metrics_report` — DESCRIPTIVE TELEMETRY ONLY, not an evaluation, benchmark or baseline: amendment rate, withdrawal rate, objection-follow-through rate, and tool-call usage, deriv - `list_runs` — Runs on disk, newest first, with state and cost. - `run_status` — State of one run: stage reached, panel verdicts, scoreboard, files produced, cost. Pass brief=true for a short, regenerated-on-demand resume brief instead - wha - `read_run_file` — Read a file from a run folder (deliverable.md, BOARD.md, HANDOFF.md, proposals.md, build.md, revise-1.md, panel-1-.md, run.log, report.json; report-partial - `plan_outline` — Section tree of a run's deliverable (or any markdown file) with word counts and the build-volume heuristic, plus the scope ledger if present. - `write_task` — Write or overwrite a task file under tasks/ (the request the harness plans against). ## Install **Verdict: review** — Installable, but 1 thing to check first: No publisher has proved control of this listing; it is indexed, not vouched for. **Cautions** (coverage gaps and advisories — never blocking) - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"the-high-council\": {\n \"command\": \"npx\",\n \"args\": [\n \"-y\",\n \"the-high-council\"\n ],\n \"env\": {\n \"ANTHROPIC_API_KEY\": \"\",\n \"OPENAI_API_KEY\": \"\",\n \"GOOGLE_API_KEY\": \"\",\n \"MISTRAL_API_KEY\": \"\",\n \"DEEPSEEK_API_KEY\": \"\",\n \"GROQ_API_KEY\": \"\",\n \"TOGETHER_API_KEY\": \"\",\n \"COHERE_API_KEY\": \"\",\n \"OPENROUTER_API_KEY\": \"\",\n \"ZAI_API_KEY\": \"\"\n }\n }\n }\n}" ``` **Credentials it will ask for** (names only — Forge never holds a value): - `ANTHROPIC_API_KEY` — Anthropic API Key (optional) - `OPENAI_API_KEY` — OpenAI API Key (optional) - `GOOGLE_API_KEY` — Google API Key (optional) - `MISTRAL_API_KEY` — Mistral API Key (optional) - `DEEPSEEK_API_KEY` — Deepseek API Key (optional) - `GROQ_API_KEY` — Groq API Key (optional) - `TOGETHER_API_KEY` — Together API Key (optional) - `COHERE_API_KEY` — Cohere API Key (optional) - `OPENROUTER_API_KEY` — Openrouter API Key (optional) - `ZAI_API_KEY` — Zai API Key (optional) Placeholders only. Forge never holds, brokers, or transmits a credential value — replace each in your own config file. Do not send a value back to Forge; no Forge endpoint accepts one. - This entry needs 10 credentials (0 required). The generated config carries placeholders, so it will fail in the editor rather than at runtime if they are left unset. ## Blast radius Extensive blast radius — mutates data; holds an api key. - Floor 49, ceiling 49 (tier: extensive) - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/the-high-council - Install plan: https://forgeregistry.com/api/v1/packages/the-high-council/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/the-high-council - HTML page: https://forgeregistry.com/registry/the-high-council - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.