// SCAN REPORT

Memvid

40 tools. 17 can modify or destroy data without limits.

1 destructive tool with no built-in limits. Policy required.

Last updated: 30 Jun 2026

17 can modify or destroy data

23 read-only

40 tools total

Community server · catalogue entry verified 30/06/2026

How to control Memvid ↓

TOOL MAP

What Memvid exposes to your agents

Read (23) Write / Execute (16) Destructive / Financial (1)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Memvid tools

Destructive · High memvid_delete The tool permanently deletes data (a frame from a memory file) with no ability to undo the operation. Execute · Medium memvid_nudge This tool executes background processes rather than simply reading or writing data in a reversible way. Execute · Medium memvid_session Session management involves triggering stateful operations: starting a new session, stopping an active one, or replaying a recorded session. Execute · Medium memvid_enrich This tool executes an NER enrichment process that modifies or annotates memory file content by extracting and storing entities.

17 of Memvid's 40 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Memvid

PolicyLayer is an MCP gateway — it sits between your AI agents and Memvid, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "memvid_delete": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "memvid_api_fetch": {
    "limits": [
      {
        "counter": "memvid_api_fetch_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "memvid_ask": {
    "limits": [
      {
        "counter": "memvid_ask_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Memvid — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON MEMVID →

Instant setup, no code required.

FULL CATALOGUE

All 40 Memvid tools

DESTRUCTIVE 1 tools

Destructive memvid_delete Delete a specific frame from memory. This operation is destructive and cannot be undone. Args: file:

EXECUTE 5 tools

Execute memvid_enrich Run Named Entity Recognition (NER) enrichment to extract entities. Extracts entities like people, organizat Execute memvid_nudge Nudge operations - trigger background processing. Forces processing of pending operations like: - Index up Execute memvid_process_queue Process pending operations queue. Executes any queued operations such as: - Deferred index updates - Batc Execute memvid_session Session management - list, start, stop, or replay sessions. Sessions track agent interactions for replay an Execute memvid_sketch Sketch operations using SimHash for near-duplicate detection. Sketches enable fast similarity detection bet

WRITE 11 tools

Write memvid_api_fetch Fetch content from a URL and add to memory. Supports web pages, APIs, and document URLs. Args: file: Write memvid_binding Memory binding operations - show or unbind. Bindings associate memory files with specific contexts or agent Write memvid_correct Correct/amend content of a frame. Creates a correction record preserving the original content for audit pur Write memvid_create Create a new .mv2 memory file for storing AI agent memories. The .mv2 format is a SQLite-based memory store s Write memvid_doctor Diagnose and repair a memory file. Can rebuild corrupted indexes: - Time index: chronological ordering - Write memvid_export Export memory data to JSON, CSV, or JSONL format. Args: file: Path to the .mv2 memory file output: Ou Write memvid_lock Encrypt a memory file. Creates an encrypted .mv2e file using AES-256-GCM encryption. The original .mv2 fil Write memvid_put Add content to a memory file from a file or directory. Supports: text, markdown, code, PDF, images (OCR). Use Write memvid_put_many Batch add multiple files from a directory with progress tracking. Optimized for large directories with comm Write memvid_unlock Decrypt an encrypted memory file. Decrypts a .mv2e file back to .mv2 format. Args: file: Path to the Write memvid_update Update content of a specific frame. Replaces the entire content of the frame. For partial corrections, use

READ 23 tools

Read memvid_ask Ask a question using RAG (Retrieval-Augmented Generation). Retrieves relevant context from memory and synth Read memvid_audit Generate an audit report with sources and citations. Creates a detailed report showing which sources suppor Read memvid_config Show current configuration. Displays configuration from: - embedder.toml (embedding model settings) - llm Read memvid_debug_segment Debug segment information (internal structure). Shows internal index structure for debugging. Segment ty Read memvid_facts Fact extraction - list facts or extract from frame. Facts are structured assertions extracted from content. Read memvid_find Search in a memory file using hybrid, lexical, or vector search. Search modes: - hybrid (default): Combines l Read memvid_follow Follow entity relationships in the knowledge graph. Traverses the entity graph starting from a given entity Read memvid_memories Memory card operations - list, stats, or filter by entity. Memory cards are structured summaries of stored Read memvid_models List available embedding models. Shows models configured in embedder.toml. Model types: - text: Text em Read memvid_open Open and display information about a memory file. Returns metadata including: - Frame count - Index sizes Read memvid_schema Schema operations - infer or show schema summary. Can infer schemas from stored data or show existing schem Read memvid_state State management - show current memory state. Shows active session, binding status, and processing queue. Read memvid_stats Show detailed statistics for a memory file. Returns: { Read memvid_status Show system status. Displays: - Memvid version - NER model status - Embedder configuration - LLM config Read memvid_tables List internal SQLite tables and structures. Shows database schema for advanced debugging. Args: file: Read memvid_timeline Show chronological timeline of frames. Returns frames ordered by creation time. Args: file: Path to t Read memvid_vec_search Vector-only similarity search (semantic search). Uses vector embeddings for semantic similarity matching. Read memvid_verify Verify integrity of a memory file. Checks: - SQLite database integrity - Index consistency - Frame check Read memvid_verify_single_file Verify integrity of a single frame. Checks: - Content checksum - Metadata integrity - Index consistency Read memvid_version Print memvid version information. Returns: Version string (e.g., Read memvid_view View content of a specific frame by ID. Args: file: Path to the .mv2 memory file frame_id: Frame ID ( Read memvid_when Temporal search - find when something was mentioned. Searches for content and returns results with temporal Read memvid_who Entity lookup - find information about an entity. Searches for entity mentions and related information.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Memvid

Can an AI agent delete data through the Memvid MCP server? +

Yes. The Memvid server exposes 1 destructive tools including memvid_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Memvid? +

The Memvid server has 11 write tools including memvid_api_fetch, memvid_binding, memvid_correct. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Memvid.

How many tools does the Memvid MCP server expose? +

40 tools across 4 categories: Destructive, Execute, Read, Write. 23 are read-only. 17 can modify, create, or delete data.

How do I enforce a policy on Memvid? +

Register the Memvid MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Memvid tool call.

Deterministic rules across all 40 Memvid tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MEMVID →

Instant setup, no code required.

40 Memvid tools catalogued and risk-classified — across an index of 43,000+ MCP servers.