Chunk, embed, and store a text. Idempotent. Full-text sources only. Requires OPENAI_API_KEY + SUPABASE_URL + SUPABASE_SERVICE_ROLE_KEY. Returns: { chunksWritten, chunksDropped, skippedDuplicate, title, sourceId }
AI agents use library_ingest to create or update resources in Alexandria MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Alexandria MCP environment.
This tool writes new data to a database by chunking, embedding, and storing text. It is idempotent (re-running doesn't create duplicates), so it's not destructive. It doesn't execute code or move money. The primary action is creating/storing data, making it a Write operation. Medium severity because it can introduce arbitrary content into the library index, potentially polluting the search corpus.
From the tool's definition 'Chunk, embed, and store a text. Idempotent.' — the tool processes and persists new data (chunks and embeddings) into storage (Supabase).
Attacks that exploit this kind of access
Chunk, embed, and store a text. Idempotent. Full-text sources only. Requires OPENAI_API_KEY + SUPABASE_URL + SUPABASE_SERVICE_ROLE_KEY. Returns: { chunksWritten, chunksDropped, skippedDuplicate, title, sourceId }. It is categorised as a Write tool in the Alexandria MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Alexandria MCP server in PolicyLayer and add a rule for library_ingest: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Alexandria MCP. Nothing to install.
library_ingest is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the library_ingest rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for library_ingest. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
library_ingest is provided by the Alexandria MCP server (the-40-thieves/alexandria-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →