Ingest a single source record into Anchord. The record is matched to an
AI agents use ingest_record to create or update resources in Anchord MCP — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Anchord MCP environment.
This tool creates or modifies data by ingesting source records into the Anchord system. It is reversible (records can be unlinked via unlink_source_record and presumably deleted), so it does not qualify as Destructive. It is not a read-only operation (get_entity, get_entity_export), nor does it execute arbitrary code or move money.
From the tool's definition Tool name is 'ingest_record' and description states 'Ingest a single source record into Anchord. The record is matched to an' (description appears truncated).
Attacks that exploit this kind of access
Ingest a single source record into Anchord. The record is matched to an. It is categorised as a Write tool in the Anchord MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Anchord MCP server in PolicyLayer and add a rule for ingest_record: 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 Anchord MCP. Nothing to install.
ingest_record 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_record 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_record. 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_record is provided by the Anchord MCP server (nolenation04/anchord-mcp). 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 →