// MCP TOOL REFERENCE

ALEXANDRIA TOOLS

20 tools from the Alexandria MCP Server, categorised by risk level.

View the Alexandria policy → Token cost: 3,573 tokens →

// ALL 20 ALEXANDRIA TOOLS

READ 13 tools

Read alexandria_ask DEFAULT TOOL — Use this for any task that could benefit from specialist expertise. Routes to the best speci... Read alexandria_audit Submit an agent output for causal audit — checks if the output reached the right conclusion through sound r... Read alexandria_capabilities Discover the full Alexandria platform — not just the 7 MCP tools, but the complete feature surface includin... Read alexandria_get_tools Export all Alexandria agents as OpenAI-compatible function-calling JSON schemas. Useful for integrating Ale... Read alexandria_grade Grade any output against a rubric. Returns per-criterion scores (0.0-1.0) and an overall pass/fail. Use to ... Read alexandria_health Check Alexandria API health and service status. Read alexandria_learn Store a learning or insight into Alexandria's memory system. This helps agents improve over time by remembe... Read alexandria_list_agents List all available specialist agents in Alexandria. Returns agents grouped by team with their names, roles,... Read alexandria_outcome Record a real-world outcome for a previously-executed agent task. 48 hours after each execution, Alexandria... Read alexandria_recommend_learnings Search Alexandria's learnings memory for insights relevant to a query. Uses RAPTOR hierarchical search — re... Read alexandria_spend Report token consumption and USD spent on Alexandria agents. Defaults to a 7-day summary with top-5 agents ... Read alexandria_status Check the status of a long-running Alexandria job (operator run, debate, council, or DNA competition). Use ... Read alexandria_tournament View agent tournament rankings and results. Tournaments score agents on standardized tasks — higher ELO mea...

WRITE 1 tools

Write alexandria_generate_image Generate an image from a text prompt. Supports multiple providers: gemini (Nano Banana, default), openai (D...

EXECUTE 6 tools

Execute alexandria_council Run the LLM Council — 5 advisor archetypes (contrarian, first-principles, expansionist, outsider, executor)... Execute alexandria_debate Run inter-agent debates for adversarial analysis. Pits agents against each other to stress-test ideas. Mode... Execute alexandria_doctor Run a self-diagnostic check on the Alexandria platform. Verifies: API connectivity, provider key status, .a... Execute alexandria_operator Run multi-agent goal decomposition. Breaks a high-level goal into 2-6 agent steps and executes them sequent... Execute alexandria_premortem Run a pre-mortem failure analysis on a plan or task before execution. Returns failure modes with probabilit... Execute alexandria_run_agent Run a specific named Alexandria agent directly on a task. Use this when you know exactly which specialist y...

// RUNNING THIS SERVER

The managed route: connect Alexandria through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y mcp-server-alexandria

// FAQ

How many tools does the Alexandria MCP server have? +

The Alexandria MCP server exposes 20 tools across 3 categories: Read, Write, Execute.

How do I enforce policies on Alexandria tools? +

Route the Alexandria server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Alexandria tools fall into? +

Alexandria tools are categorised as Read (13), Write (1), Execute (6). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.