get_local_doc
AI agents call get_local_doc to retrieve information from MCP Local Context without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves or fetches a local document without modifying or deleting it. While the description is empty, the name and context from related tools and server purpose (documentation access and RAG) make it clear this performs a data retrieval operation with no side effects. Confidence is slightly reduced due to empty tool description, but naming convention and sibling context are reliable indicators.
From the tool's definition Tool name 'get_local_doc' combined with server description stating it enables 'access and search local documents.' The pattern of sibling tools (list_docs_by_type, list_local_docs, search_local_docs, semantic_search) all being read operations, and the name…
Attacks that exploit this kind of access
get_local_doc. It is categorised as a Read tool in the MCP Local Context MCP Server, which means it retrieves data without modifying state.
Register the MCP Local Context MCP server in PolicyLayer and add a rule for get_local_doc: 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 MCP Local Context. Nothing to install.
get_local_doc 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 get_local_doc 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 get_local_doc. 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.
get_local_doc is provided by the MCP Local Context MCP server (steedmonteiro/mcp-local-context). 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 →