Getting it into your agent
This one installs as part of its plugin. Adding the marketplace and installing the plugin brings it with everything else the plugin ships.
/plugin marketplace add tsarihan/model-council-mcp/plugin install model-councilWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/mcp/tsarihan/model-council-mcp/model-council)<a href="https://agentmods.dev/mcp/tsarihan/model-council-mcp/model-council"><img src="https://agentmods.dev/badge/mcp/tsarihan/model-council-mcp/model-council/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/mcp/tsarihan/model-council-mcp/model-council"><img src="https://agentmods.dev/badge/mcp/tsarihan/model-council-mcp/model-council.svg" alt="Reviewed on agentmods" width="80" height="20"></a>Grade A, and why
model-council scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
Copies of this mod
1 near-identical copy found in the catalogue:
- model-council — 100% identical, 0 lines differ
How it starts
The opening of the file, as written. The whole thing — 45 lines — stays where its author put it; the contents beside it link to each section on GitHub.
{
"model-council": {
"command": "node",
"args": [
"${CLAUDE_PLUGIN_ROOT}/bundle/server.cjs"
],
"env": {
"OLLAMA_ADDRESS": "${user_config.ollama_address}",
"COUNCIL_MODELS": "${user_config.council_models}",
"AUTO_COUNCIL": "${user_config.auto_council}",
"JUDGE_MODEL": "${user_config.judge_model}",
"RESPONSE_MODE": "${user_config.response_mode}",
"MAX_DECONFLICT_ROUNDS": "${user_config.max_deconflict_rounds}",
"OPENAI_API_KEY": "${user_config.openai_api_key}",
"ANTHROPIC_API_KEY": "${user_config.anthropic_api_key}",
"XAI_API_KEY": "${user_config.xai_api_key}",
"VLLM_SERVERS": "${user_config.vllm_servers}",
"TRTLLM_SERVERS": "${user_config.trtllm_servers}",
"SGLANG_SERVERS": "${user_config.sglang_servers}",
"MAX_TOKENS": "${user_config.max_tokens}",
"REASONING_EFFORT": "${user_config.reasoning_effort}",
"WEB_ACCESS": "${user_config.web_access}",
"COUNCIL_SESSIONS": "${user_config.council_sessions}",
"CLOUD_CONCURRENCY": "${user_config.cloud_concurrency}",
"LOCAL_CONCURRENCY": "${user_config.local_concurrency}",
"COMPLETION_RETRIES": "${user_config.completion_retries}",
"REQUEST_TIMEOUT_MS": "${user_config.request_timeout_ms}",
"REPO_REQUEST_TIMEOUT_MS": "${user_config.repo_request_timeout_ms}",
"DECONFLICT_VERBOSE": "${user_config.deconflict_verbose}",
"CLAUDE_CLI": "${user_config.claude_cli}",
"CLAUDE_CLI_MODELS": "${user_config.claude_cli_models}",
"CLAUDE_CLI_PATH": "${user_config.claude_cli_path}",
"CODEX_CLI": "${user_config.codex_cli}",
"CODEX_CLI_MODELS": "${user_config.codex_cli_models}",
"CODEX_CLI_PATH": "${user_config.codex_cli_path}",
"GROK_CLI": "${user_config.grok_cli}",
"GROK_CLI_MODELS": "${user_config.grok_cli_models}",
"GROK_CLI_PATH": "${user_config.grok_cli_path}",
"CLAUDE_TIER": "${user_config.claude_tier}",
"CHATGPT_TIER": "${useWhat this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 45 lines scan A 7b394304c3b3
model-council is an MCP server published in the GitHub repository tsarihan/model-council-mcp (1 stars, last pushed 1mo ago), licensed Apache-2.0. Its token cost is not measured: an MCP server costs its tool schemas, not its config file. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.
Other mcp servers, from other repositories
docs-langchain
MCP server "docs-langchain", hosted remotely at docs.langchain.com, as configured in langchain-ai/langchain.
component-explorer
MCP server "component-explorer" as configured in microsoft/vscode. Launched with npm exec --no -- component-explorer mcp -p ./test/componentFixtures/component-ex.
vscode-automation-mcp
MCP server "vscode-automation-mcp" as configured in microsoft/vscode. Launched with npm run start-stdio.
reference-langchain
MCP server "reference-langchain", hosted remotely at reference.langchain.com, as configured in langchain-ai/langchain.
supabase
Supabase's hosted MCP server: lets the agent manage projects, tables, SQL and migrations. Remote server at mcp.supabase.com.
playwright-test
A high-level API to automate web browsers. Runs locally from the playwright npm package.