This record as markdown: /tools/io-github-portel-dev-ncp/index-document.md
What index_document does on Ncp
AI agents use index_document to create or update resources in Ncp, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Ncp environment.
Why index_document is rated Medium
Indexing a document in Elasticsearch creates or modifies searchable data in the index. This is a Write operation because it persists data reversibly (indexed documents can be updated or removed). It is not Read (no retrieval), Execute (no arbitrary command execution), Destructive (indexing does not irreversibly delete data), or Financial.
From the tool's definition Tool name 'index_document' combined with description 'Index document in Elasticsearch' indicates the tool writes/stores document data into an Elasticsearch index.
Attacks that exploit this kind of access
The rule that runs index_document safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Ncp, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For index_document, this is the rule to start with:
index_document 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.
The button opens the PolicyLayer dashboard: create your workspace, connect Ncp, apply this rule, and every index_document call is checked against it from then on.
Questions about index_document
Index document in Elasticsearch. It is categorised as a Write tool in the Ncp MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Ncp MCP server in PolicyLayer and add a rule for index_document: 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 Ncp. Nothing to install.
index_document 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_document 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_document. 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_document is provided by the Ncp MCP server (@portel/ncp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Ncp, and thousands of servers like it.
This server
Across the catalogue