Dry run: fetch text, chunk semantically, score OCR quality. No writes. Full-text sources only. Returns: { totalChunks, droppedChunks, avgQualityScore, estimatedTokens, sampleChunks[0..2] }
AI agents call library_index to retrieve information from Alexandria MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool explicitly states it is a dry run with no writes. It fetches and analyzes text (chunking and OCR quality scoring) but makes no modifications to any data store. It only returns analysis results like chunk counts, quality scores, and token estimates. This is purely a read/analysis operation.
From the tool's definition Dry run: fetch text, chunk semantically, score OCR quality. No writes.
Attacks that exploit this kind of access
Dry run: fetch text, chunk semantically, score OCR quality. No writes. Full-text sources only. Returns: { totalChunks, droppedChunks, avgQualityScore, estimatedTokens, sampleChunks[0..2] }. It is categorised as a Read tool in the Alexandria MCP MCP Server, which means it retrieves data without modifying state.
Register the Alexandria MCP server in PolicyLayer and add a rule for library_index: 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_index is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the library_index 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_index. 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_index 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 →