Semantic search over evidence_log rows. Embeds the query and every (title + body) pair, ranks by cosine similarity, returns the top-N matches with their scores. v1.1 first cut uses a deterministic signed-hash-bag embedder; a real local model will land in a follow-up behind the same async interface.
AI agents call recall to retrieve information from Slopweaver without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The recall tool is a pure retrieval and ranking operation. It searches and returns matching data without modifying, deleting, or executing any operations. The use of embedding and similarity ranking does not elevate this beyond a Read operation. The deterministic nature and local-first context confirm this is a passive data retrieval tool with minimal blast radius if misused.
From the tool's definition Tool performs "Semantic search over evidence_log rows" with "Embeds the query and every (title + body) pair, ranks by cosine similarity, returns the top-N matches". No mutations, deletions, or side effects described.
Attacks that exploit this kind of access
Semantic search over evidence_log rows. Embeds the query and every (title + body) pair, ranks by cosine similarity, returns the top-N matches with their scores. v1.1 first cut uses a deterministic signed-hash-bag embedder; a real local model will land in a follow-up behind the same async interface. It is categorised as a Read tool in the Slopweaver MCP Server, which means it retrieves data without modifying state.
Register the Slopweaver MCP server in PolicyLayer and add a rule for recall: 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 Slopweaver. Nothing to install.
recall 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 recall 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 recall. 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.
recall is provided by the Slopweaver MCP server (slopweaver/slopweaver). 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 →