MCP SERVERS

Agents use MCP tools — filesystem, browser, databases, any MCP server

Council agents can call any MCP server during deliberation. File system access, browser automation, database queries, Slack messaging — any tool available via MCP becomes available to your agents. The same protocol Claude and other AI tools use.

WHAT AGENTS SEE

MCP tools appear as callable functions. Agent writes TOOL_REQUEST: mcp_server.tool_name params → Council routes to the MCP server → result injected into next round.

LIVE EXAMPLE

Council deliberates a technical architecture decision. Agents use MCP to access real project data.

ARCH-01:MCP: filesystem.read_file("src/auth/middleware.py")

Read the actual implementation — found 3 security patterns that constrain the redesign.

PERF-01:MCP: postgres.query("SELECT avg(latency) FROM requests WHERE path LIKE '/auth%'")

Auth endpoints average 340ms — already slow. Proposed change would add another layer.

DOCS-01:MCP: confluence.search("auth migration plan")

Found existing migration plan from Q1 — 60% overlaps with this proposal. Don't duplicate.

◈ Synthesis:

RECOMMENDATION: Adapt the Q1 migration plan instead of starting fresh. Address the 340ms latency as part of the migration, not as a separate effort. The 3 security patterns in middleware.py must be preserved.

GET CONNECTED

1

Register MCP servers

In ecosystem settings, add MCP server configs: command, args, env vars.

{"name": "project_fs", "type": "mcp", "transport": "stdio", "mcp_command": "npx", "mcp_args": ["-y", "@anthropic-ai/mcp-server-filesystem", "/path/to/project"]}
2

Discover tools automatically

Council calls list_tools() on each MCP server at startup. Tools appear as agent capabilities.

3

Scope per agent

Each agent's ## Tools section whitelists which MCP tools they can call.

4

Works with any MCP server

Anthropic's official servers, community servers, or your own custom MCP implementations.

▸ CONNECT MCP SERVERS