Index Markdown files for semantic search using Milvus.
AI agents use index_documents to create or update resources in MCP-Markdown-RAG — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your MCP-Markdown-RAG environment.
This tool reads local Markdown files and writes/creates vector embeddings into a Milvus database index. It is a Write operation as it creates new index entries in the vector database. Misuse could result in indexing unintended files or consuming significant resources, but it is reversible (the index can be cleared via the sibling clear_index tool).
From the tool's definition Index Markdown files for semantic search using Milvus
Documented attack patterns abuse exactly the kind of access index_documents gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and MCP-Markdown-RAG, and nothing reaches the server without passing your rules. This is the rule we recommend for index_documents:
{
"version": "1",
"default": "deny",
"tools": {
"index_documents": {
"limits": [
{
"counter": "index_documents_rate",
"window": "minute",
"max": 30,
"scope": "grant"
}
]
}
}
}index_documents stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Index Markdown files for semantic search using Milvus. It is categorised as a Write tool in the MCP-Markdown-RAG MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the MCP-Markdown-RAG MCP server in PolicyLayer and add a rule for index_documents: 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-Markdown-RAG. Nothing to install.
index_documents 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 index_documents 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 index_documents. 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.
index_documents is provided by the MCP-Markdown-RAG MCP server (zackriya-solutions/mcp-markdown-rag). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Deterministic rules across all 3 MCP-Markdown-RAG tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.
Free to start. No card required.
3 MCP-Markdown-RAG tools catalogued and risk-classified — across an index of 42,500+ MCP servers.