About Model Council
Model Council is an MCP server published by Totti0135 in the AI category: consult other LLMs as tools — ask them, compare their answers, synthesize a conclusion.
The repository has 2 stars and 0 forks, with the last commit 2 months ago. Recent commit activity is the strongest signal that reported issues will get attention.
Install
uvx
uvx model-council-mcppip
pip install model-council-mcpThis server has no ConduID identity, so agent calls to it are not receipted. Pin the version you install and review the source before granting it credentials.
Tools (6)
ask(model, prompt, materials?)Ask one member by id
Parameters not published.
ask_all(prompt, models?, rounds?, guests?, materials?, steelman?)Ask everyone (or a named subset) the same prompt in parallel, answers side by side. `rounds=2` turns it into a discussion; `steelman` seats a standing objection that argues back every round; `guests` seats answers you already have; `materials` hands them a file to read
Parameters not published.
list_council()The roster: ids, endpoints, weights, what each member can be shown, the route each takes out, call budget, and whether it is ready. No network calls
Parameters not published.
probe_models(model?)Ask a provider's `/models` route what ids it really exposes
Parameters not published.
revise(prompt, answers, round?, materials?)Run one more round yourself: show the members everything said last round — including answers only you can produce — and get them back revised
Parameters not published.
revision_prompt(prompt, answers, seat, materials?)The prompt to hand your own seat for the next round, word-for-word what the members got. No network calls
Parameters not published.
Ask AI
✦
Ask AI about Model Council
Powered by Claude · Grounded in docs
I know everything about Model Council. Ask me about installation, configuration, usage, or troubleshooting.
Security checks
6 checks have not been run yet.