agenticow_ingest
agenticow — write vectors (with optional text payloads) into an .rvf memory branch or base. Records: [{id?, vector, text?}] — id auto-assigns when omitted. This is the write half that makes a branch usable: agenticow_branch creates an empty COW child, but without ingest it has nothing to read bac...
This record as markdown: /tools/io-github-ruvnet-claude-flow/agenticow-ingest.md
What agenticow_ingest does on Claude Flow
AI agents use agenticow_ingest to create or update resources in Claude Flow, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Claude Flow environment.
Why agenticow_ingest is rated Medium
The tool creates or modifies data (vectors and optional text payloads) in a branched memory store in a reversible manner. It does not execute arbitrary code, delete data, move money, or read existing data—it writes new records to a Copy-on-Write (COW) structure that can be promoted or discarded.
From the tool's definition Tool description explicitly states 'write vectors (with optional text payloads) into an .rvf memory branch or base' and 'This is the write half that makes a branch usable'. The operation creates and populates records reversibly.
Attacks that exploit this kind of access
The rule that runs agenticow_ingest safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Claude Flow, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For agenticow_ingest, this is the rule to start with:
agenticow_ingest 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 Claude Flow, apply this rule, and every agenticow_ingest call is checked against it from then on.
Questions about agenticow_ingest
agenticow — write vectors (with optional text payloads) into an .rvf memory branch or base. Records: [{id?, vector, text?}] — id auto-assigns when omitted. This is the write half that makes a branch usable: agenticow_branch creates an empty COW child, but without ingest it has nothing to read back. Use when you have branched and must populate the branch (agenticow_branch alone leaves it empty). Editing the base directly is wrong when the writes are speculative — ingest into a branch, then promote only if validated. Persists via .agenticow.json lineage manifest. It is categorised as a Write tool in the Claude Flow MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Claude Flow MCP server in PolicyLayer and add a rule for agenticow_ingest: 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 Claude Flow. Nothing to install.
agenticow_ingest 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 agenticow_ingest 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 agenticow_ingest. 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.
agenticow_ingest is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Claude Flow, and thousands of servers like it.
This server
Across the catalogue