recall_similar_work

Read-only vault search: rank past memory notes by similarity to a new visual goal so the agent can reuse prior recipes, params, and prompts instead of rebuilding from scratch. Scores by query-token overlap with title/intent/prompt/tags/body, with optional tag and op boosts. Returns ranked hits wi...

Low RISK CLASS
Category Read
Parameters 00 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-pantani-tdmcp/recall-similar-work.md

What recall_similar_work does on tdmcp — TouchDesigner MCP server

AI agents call recall_similar_work to retrieve information from tdmcp — TouchDesigner MCP server without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why recall_similar_work is rated Low

This is a straightforward search/query utility that retrieves and ranks existing vault entries. It has no side effects, cannot modify data, and operates entirely within the TouchDesigner project context. The read-only designation and return-only behavior clearly place it in the Read category with low severity and high confidence.

From the tool's definition Tool is explicitly described as 'Read-only vault search' that 'rank[s] past memory notes' and 'Returns ranked hits'. The tool only searches and retrieves data (scores, vault paths, matched terms, snippets) with no modifications, deletions, or external effects.

Questions about recall_similar_work

What does the recall_similar_work tool do? +

Read-only vault search: rank past memory notes by similarity to a new visual goal so the agent can reuse prior recipes, params, and prompts instead of rebuilding from scratch. Scores by query-token overlap with title/intent/prompt/tags/body, with optional tag and op boosts. Returns ranked hits with vault paths, score, matched terms, and an optional body snippet. Offline; requires TDMCP_VAULT_PATH. It is categorised as a Read tool in the tdmcp — TouchDesigner MCP server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on recall_similar_work? +

Register the tdmcp — TouchDesigner MCP server MCP server in PolicyLayer and add a rule for recall_similar_work: 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 tdmcp — TouchDesigner MCP server. Nothing to install.

What risk level is recall_similar_work? +

recall_similar_work is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit recall_similar_work? +

Yes. Add a rate_limit block to the recall_similar_work 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.

How do I block recall_similar_work completely? +

Set action: deny in the PolicyLayer policy for recall_similar_work. 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.

What MCP server provides recall_similar_work? +

recall_similar_work is provided by the tdmcp — TouchDesigner MCP server MCP server (@dpantani/tdmcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

More on tdmcp — TouchDesigner MCP server, and thousands of servers like it.

Across the catalogue

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of tdmcp — TouchDesigner MCP server's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.