AI agents call get_ingest_job to retrieve information from Sfgraph without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves the state of an existing ingest job without modifying, executing, or deleting anything. It is a pure query/fetch operation with no side effects, fitting the Read category. The clarification that the server does not run ingest workers confirms no execution occurs. Severity is low because misuse cannot cause harm—only information retrieval is possible.
From the tool's definition Tool name 'get_ingest_job' and description 'Fetch state of an in-process ingest job by id' indicates a retrieval operation with no side effects. The note clarifies the server does not execute ingest workers, further confirming this is a status query only.
Attacks that exploit this kind of access
Fetch state of an in-process ingest job by id. NOTE: the MCP server does not run ingest workers —. It is categorised as a Read tool in the Sfgraph MCP Server, which means it retrieves data without modifying state.
Register the Sfgraph MCP server in PolicyLayer and add a rule for get_ingest_job: 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 Sfgraph. Nothing to install.
get_ingest_job 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_ingest_job 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_ingest_job. 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_ingest_job is provided by the Sfgraph MCP server (ryanstark24/sfgraph). 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 →