// MCP TOOL REFERENCE

TOTAL RECALL TOOLS

30 tools from the Total Recall MCP Server, categorised by risk level.

// ALL 30 TOTAL RECALL TOOLS

READ 17 tools

Read dismiss_suggestion Dismiss a pending behavioral suggestion. It won Read get_budget Get current context budget usage and availability. Shows total tokens, allocation by slice, and remaining c... Read get_suggestions View pending knowledge suggestions from the behavioral learning engine. These are patterns Total Recall det... Read health_check Run a comprehensive health check on Total Recall. Returns database integrity status, table counts, session ... Read load_context Load relevant knowledge entries based on a message and project context. Uses smart loading with relevance s... Read query_dependencies Query the dependency graph for a component. Returns all components that depend on it or that it depends on,... Read recall Search the knowledge base using a natural language query. Returns matching entries ranked by relevance. Use... Read recall_by_category Retrieve all active knowledge entries in a specific category. Useful for loading all decisions, all correct... Read recall_by_id Retrieve a single knowledge entry by its UUID. Use when you have a specific entry ID. Read recall_semantic Search knowledge using semantic TF-IDF ranking. Better than keyword search for natural language questions like Read remember Store a new piece of knowledge in the Total Recall memory system. Use this to persist facts, decisions, err... Read session_state_read Read the current session state. Call this before generating any response to refresh your memory of what hap... Read sync Sync knowledge between local SQLite and Supabase cloud. Push local changes, pull remote changes, or both. R... Read task_list List multi-session tasks, optionally filtered by project or status. Read verify_claim Verify a claim against stored decisions and facts in the knowledge base. Returns VERIFIED, CONFLICT, or UNK... Read verify_file Verify that a file exists, has content, and is optionally tracked in git. Returns VERIFIED, FAILED, or STALE. Read verify_push Verify that local HEAD matches remote HEAD for a repository branch.

WRITE 8 tools

Write add_dependency Add a dependency relationship between two components in a project. Used to track impact of changes. Write approve_suggestion Approve a pending behavioral suggestion, promoting it to permanent knowledge. Write delegate Create a delegation package for handing off a task to another agent with full context. Includes relevant de... Write export_knowledge Export all active knowledge and sessions to a JSON file for git backup or transfer. Write session_close Close the current session. Call this at the end of every conversation. Triggers final state save, audit, an... Write session_state_write Update the session state. Call this after every response that involves tool calls, file operations, decisio... Write task_create Create a multi-session task for tracking work across conversations. Write task_update Update a multi-session task

DESTRUCTIVE 2 tools

Destructive forget Archive a knowledge entry (soft-delete). The entry is preserved but no longer auto-loaded. Use when knowled... Destructive remove_dependency Remove a dependency relationship by its ID.

EXECUTE 3 tools

Execute correct Record a correction — the highest-priority knowledge type. Creates a new correction entry that supersedes a... Execute doctor Run diagnostic checks and repair common issues. Checks database integrity, orphaned session files, checksum... Execute session_start Start a new Total Recall session. Call this at the beginning of every conversation. Returns session_id and ...

// RUNNING THIS SERVER

The managed route: connect Total Recall through the PolicyLayer gateway — every tool call above is checked against your policy before it runs, with a full audit log.

DIRECT INSTALL (UNMANAGED) npx -y @avi-total-recall/total-recall

// FAQ

How many tools does the Total Recall MCP server have? +

The Total Recall MCP server exposes 30 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Total Recall tools? +

Route the Total Recall server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Total Recall tools fall into? +

Total Recall tools are categorised as Read (17), Write (8), Destructive (2), Execute (3). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.