📊 Extract and linearize tables from markdown, HTML, or CSV content. Produces structured table data, linearized text for vector embedding, and chunks for RAG retrieval.
AI agents call indexfoundry_extract_tables to retrieve information from IndexFoundry MCP without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool reads and processes existing table data from markdown, HTML, or CSV content to produce structured outputs for embedding and RAG purposes. There are no side effects, data modifications, deletions, or external operations triggered. The blast radius of misuse is minimal — an agent could extract tables from unintended sources, but this causes no harm to the underlying data or systems.
From the tool's definition Tool description states it 'Extract[s]' tables and 'Produces structured table data' — these are retrieval and transformation operations with no modification to source data.
Attacks that exploit this kind of access
📊 Extract and linearize tables from markdown, HTML, or CSV content. Produces structured table data, linearized text for vector embedding, and chunks for RAG retrieval. It is categorised as a Read tool in the IndexFoundry MCP MCP Server, which means it retrieves data without modifying state.
Register the IndexFoundry MCP server in PolicyLayer and add a rule for indexfoundry_extract_tables: 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 IndexFoundry MCP. Nothing to install.
indexfoundry_extract_tables 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 indexfoundry_extract_tables 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 indexfoundry_extract_tables. 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.
indexfoundry_extract_tables is provided by the IndexFoundry MCP server (mnehmos/mnehmos.index-foundry.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 →