recall_content

Search Mirror memory for previously published content. Use before drafting to detect duplicates or find related articles.

Server Inkwell MCP Server mumega-com/inkwell
Category Read
Risk class Low
Parameters 00 required

What recall_content does on Inkwell MCP Server

AI agents call recall_content to retrieve information from Inkwell MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.

Why recall_content needs a policy

This tool performs a query/search operation to retrieve previously published content from Mirror memory. It does not modify, create, delete, or execute any operations—it only retrieves and reads existing data. The use case (duplicate detection and research) is purely informational. There is no capability to change state, trigger external operations, or cause any destructive or financial effects.

From the tool's definition Tool name is 'recall_content' and description states 'Search Mirror memory for previously published content.' The verb 'search' and the purpose of detecting duplicates and finding related articles indicate data retrieval with no side effects.

Questions about recall_content

What does the recall_content tool do? +

Search Mirror memory for previously published content. Use before drafting to detect duplicates or find related articles. It is categorised as a Read tool in the Inkwell MCP Server MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on recall_content? +

Register the Inkwell MCP Server MCP server in PolicyLayer and add a rule for recall_content: 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 Inkwell MCP Server. Nothing to install.

What risk level is recall_content? +

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

Can I rate-limit recall_content? +

Yes. Add a rate_limit block to the recall_content 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_content completely? +

Set action: deny in the PolicyLayer policy for recall_content. 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_content? +

recall_content is provided by the Inkwell MCP Server MCP server (mumega-com/inkwell). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

// LOOK UP ANOTHER 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 →

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.