// SCAN REPORT

SQLite Project Memory MCP

41 tools. 22 can modify or destroy data without limits.

3 destructive tools with no built-in limits. Policy required.

Last updated:

22 can modify or destroy data
19 read-only
41 tools total

Community server · catalogue entry verified 03/07/2026

How to control SQLite Project Memory MCP ↓

TOOL MAP

What SQLite Project Memory MCP exposes to your agents

Read (19) Write / Execute (19) Destructive / Financial (3)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS
Critical Risk

The most dangerous SQLite Project Memory MCP tools

Destructive · High delete_entity Destructive category applies because the tool permanently deletes entities from the authoritative source of truth database. Destructive · High delete_relationship This tool permanently removes relationship data from the SQLite database. Destructive · High prune_content_retention The tool irreversibly deletes older content records from entities, keeping only the most recent ones. Execute · Medium run_read_query Although described as read-only, this tool executes arbitrary SQL queries supplied as arguments, placing it in the Execute category.

22 of SQLite Project Memory MCP's 41 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control SQLite Project Memory MCP

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

Deny destructive operations
{
  "delete_entity": {
    "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
{
  "add_relationship": {
    "limits": [
      {
        "counter": "add_relationship_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "find_similar_entities": {
    "limits": [
      {
        "counter": "find_similar_entities_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

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

  1. Create a free account and register SQLite Project Memory MCP — nothing to install.
  2. Add these rules — paste them, or build them visually. Tune the limits to your setup.
  3. Point your MCP client (Claude, Cursor, anything) at your gateway URL.
ENFORCE POLICY ON SQLITE PROJECT MEMORY →

Instant setup, no code required.

FULL CATALOGUE

All 41 SQLite Project Memory MCP tools

DESTRUCTIVE 3 tools
Destructive delete_entity Delete an entity with guardrails; non-forced deletion requires prior archiving and no critical dependents. Destructive delete_relationship Delete a relationship by id and record the removal in project history. Destructive prune_content_retention Prune older reasoning/log content while keeping the most recent records per entity and type.
EXECUTE 3 tools
Execute apply_performance_tuning Tune SQLite settings for throughput during heavy project-memory workloads. Execute refresh_task_summary Rebuild a task summary materialized table for faster open task queries. Execute run_read_query Run a constrained read-only SQL query for diagnostics, analytics, and ad hoc retrieval.
WRITE 16 tools
Write add_relationship Create a typed graph edge between two entities. Write append_content Add a piece of content to an entity. Write archive_entity Archive an entity without deleting its history or related project memory. Write bootstrap_project_memory Initialize a project root entity and standard memory-area anchor entities. Write connect_entities Create a relationship if missing, otherwise return the existing edge. Write create_entity Create a new authoritative project entity. Write create_snapshot Create a named snapshot of current project state. Write export_markdown_views Write generated markdown views only after an explicit user request for a human-readable artifact. Write get_or_create_entity Reuse an exact entity when it already exists or create one with a generated stable id. Write merge_entities Merge a duplicate source entity into a target entity with deterministic conflict handling. Write set_project_root Switch project context (root + db + export path) and reconnect database. Write set_tags Set or merge tag labels for an entity. Write update_entity Update an existing entity's top-level state. Write upsert_attributes Create or update flexible metadata for an entity. Write upsert_entity Create an entity if missing or merge updates into an existing entity. Write write_content Write narrative content in one unified API with append|replace semantics.
READ 19 tools
Read find_similar_entities Find likely duplicate or related entities before creating a new one. Read get_architecture_summary Return a compact architecture-oriented node and relationship summary. Read get_database_health Report likely duplicates, low-quality records, and retention pressure in project memory. Read get_decision_log Return decisions and recent supporting note excerpts without requiring ad hoc SQL. Read get_dependency_view Return dependency-oriented graph data with stable compact fields. Read get_entity Fetch an entity and optionally include related metadata, content, and events. Read get_entity_graph Traverse outward relationship dependencies from an entity. Read get_project_context Return the current project root, DB path, and export directory. Read get_recent_activity Return recent entities, content, and events to help an AI resume context quickly. Read get_recent_reasoning Return recent reasoning excerpts for quick AI context recovery. Read get_snapshot Fetch a named snapshot and its captured entities. Read list_entities List entities with optional type, status, attribute, tag, and text filters. Read list_relationships List graph edges, optionally constrained to an entity and direction. Read list_views List available view names for query_view discovery. Read query_view Query a named SQL view for generic reporting and model projections. Read render_markdown_views Render markdown document views only after an explicit user request for a human-readable artifact. Read resolve_entity_by_name Resolve a human-readable name to an existing entity when possible. Read search_content Search narrative content using FTS5 when available. Read server_info Return server metadata and schema settings.
EXPLORE

Related servers

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

Yaver 1060 tools
adminautomation
Nodebench 824 tools
adminautomation
UnClick 813 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Fortimanager 584 tools
adminautomation
Crow 573 tools
adminautomation
Mcp 571 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
FAQ

Questions about SQLite Project Memory MCP

Can an AI agent delete data through the SQLite Project Memory MCP server? +

Yes. The SQLite Project Memory MCP server exposes 3 destructive tools including delete_entity, delete_relationship, prune_content_retention. 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 SQLite Project Memory MCP? +

The SQLite Project Memory MCP server has 16 write tools including add_relationship, append_content, archive_entity. 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 SQLite Project Memory MCP.

How many tools does the SQLite Project Memory MCP server expose? +

41 tools across 4 categories: Destructive, Execute, Read, Write. 19 are read-only. 22 can modify, create, or delete data.

How do I enforce a policy on SQLite Project Memory MCP? +

Register the SQLite Project Memory 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 SQLite Project Memory MCP tool call.

Deterministic rules across all 41 SQLite Project Memory MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON SQLITE PROJECT MEMORY →

Instant setup, no code required.

41 SQLite Project Memory MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.