// SCAN REPORT

Engram

21 tools. 5 can modify or destroy data without limits.

5 write tools that can modify data. Rate limits recommended.

Last updated: 30 Jun 2026

5 can modify or destroy data

16 read-only

21 tools total

Community server · catalogue entry verified 30/06/2026

How to control Engram ↓

TOOL MAP

What Engram exposes to your agents

Read (16) Write / Execute (5) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Engram tools

Execute · High rebuild_index Rebuilding indexes is an Execute-category action: it triggers a potentially expensive system operation that reprocesses and reconstructs internal data structures (bloom filters, git indexes, embeddings). Write · Medium ledger_ingest This tool creates or modifies assertions in a persistent memory ledger, which is a reversible write operation. Write · Medium remember This tool creates or modifies persistent data (memories, sessions, decisions) in the Engram epistemic engine. Write · Medium receive_handoff This tool writes/injects a context blob received from another agent into the system's memory or state.

5 of Engram's 21 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Engram

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

Rate limit write operations

{
  "ledger_ingest": {
    "limits": [
      {
        "counter": "ledger_ingest_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "cross_project_search": {
    "limits": [
      {
        "counter": "cross_project_search_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 Engram — 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 ENGRAM →

Instant setup, no code required.

FULL CATALOGUE

All 21 Engram tools

EXECUTE 1 tools

Execute rebuild_index Rebuild Engram indexes (bloom, git, embeddings).

WRITE 4 tools

Write ledger_ingest Write an assertion to the ledger. Creates new or reinforces existing assertions. Write receive_handoff Receive a context blob from another agent and confirm injection. Write remember Save a memory or session to Engram. Call at end of session, after completing a feature, or when recording a de Write session_append_event Append an event to a session timeline. Agents call this during a session to record decisions, experiments, rej

READ 16 tools

Read cross_project_search Search across ALL projects semantically. Groups results by project with relevance scores. Great for finding re Read find_duplicates Find duplicate or near-duplicate sessions using embedding similarity. Returns pairs of sessions above the simi Read get_bundle Get pre-compiled context bundle for a specific project. Includes description, tech stack, recent sessions, and Read get_session Get full session details by project and session ID. Read get_topics Get top topics/tags from Engram with session counts. Read handoff Generate a portable context blob for agent-to-agent handoff. Packs project bundle, recent sessions, ledger ass Read ledger_query Query active assertions by plane. Read ledger_select_context Select and render ranked assertions for context injection. Read ledger_stats Get ledger statistics: counts by status, plane, and tensions. Read list_projects List all projects indexed in Engram with session counts. Read neural_search Semantic search across all Engram sessions. Finds sessions by meaning, not just keywords. Use this to find rel Read query_concept Look up a concept in the knowledge graph. Returns related concepts and connection strengths. Read recent_sessions Get the most recent sessions across all projects. Read search_sessions Keyword search across sessions by summary and topics. Read session_diff Compare two sessions and show what topics changed between them. Read session_replay Get the full timeline of events for a session, in chronological order.

FAQ

Questions about Engram

How do I prevent bulk modifications through Engram? +

The Engram server has 4 write tools including ledger_ingest, receive_handoff, remember. 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 Engram.

How many tools does the Engram MCP server expose? +

21 tools across 2 categories: Read, Write. 16 are read-only. 5 can modify, create, or delete data.

How do I enforce a policy on Engram? +

Register the Engram 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 Engram tool call.

Deterministic rules across all 21 Engram tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ENGRAM →

Instant setup, no code required.

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