ingest_corpus
Add a document to YOUR private searchable corpus (chunk + free local embeddings). Owner-gated. Capped per agent. Returns {ok, doc_id, chunks_stored}.
This record as markdown: /tools/com-wingmanprotocol-agent-gateway/ingest-corpus.md
What ingest_corpus does on Gateway
AI agents use ingest_corpus to create or update resources in Gateway, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Gateway environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
text | string | Yes | the document text (≤400KB; split larger) |
doc_id | string | Yes | an id/name for this document |
handle | string | Yes | your registered handle (owner-gated) |
secret | string | — | your agent secret |
Parameters from the server's own tool schema.
Why ingest_corpus is rated Medium
This tool creates and stores new data (document chunks with embeddings) in a user's private corpus, making it a Write operation. The owner-gating and per-agent caps mitigate risk by restricting who can add documents and volume. No side effects beyond storage; data remains reversible/deletable. Severity is low due to scope (private, not shared) and rate-limiting.
From the tool's definition Tool name 'ingest_corpus' with description 'Add a document to YOUR private searchable corpus' indicates creation/storage of data. Returns {ok, doc_id, chunks_stored} confirms successful write operation.
Risk signalsHandles credentials or secrets (secret)
Attacks that exploit this kind of access
The rule that runs ingest_corpus safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Gateway, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For ingest_corpus, this is the rule to start with:
ingest_corpus 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 Gateway, apply this rule, and every ingest_corpus call is checked against it from then on.
Questions about ingest_corpus
Add a document to YOUR private searchable corpus (chunk + free local embeddings). Owner-gated. Capped per agent. Returns {ok, doc_id, chunks_stored}. It is categorised as a Write tool in the Gateway MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
ingest_corpus accepts 4 parameters: text, doc_id, handle, secret. Required: text, doc_id, handle. The full parameter table on this page comes from the server's own tool schema.
Register the Gateway MCP server in PolicyLayer and add a rule for ingest_corpus: 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 Gateway. Nothing to install.
ingest_corpus 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 ingest_corpus 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 ingest_corpus. 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.
ingest_corpus is provided by the Gateway MCP server (https://wingmanprotocol.com/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Gateway, and thousands of servers like it.
This server
Across the catalogue