// SCAN REPORT

Forgetful

59 tools. 38 can modify or destroy data without limits.

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

Last updated:

38 can modify or destroy data
21 read-only
59 tools total

Community server · catalogue entry verified 11/06/2026

How to control Forgetful ↓

TOOL MAP

Read (21) Write / Execute (31) Destructive / Financial (7)

MOST DANGEROUS TOOLS

Critical Risk
Destructive · High delete_code_artifact This tool permanently and irreversibly deletes code artifacts from the knowledge base with no recovery mechanism. Destructive · High delete_document This tool irreversibly deletes data (documents and their memory associations) with no undo capability. Destructive · High delete_entity This tool irreversibly deletes data (entities and their relationships) with no undo capability. Destructive · High delete_entity_relationship This tool permanently deletes relationship records from the knowledge base without reversibility.

38 of Forgetful's 59 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

HOW TO CONTROL FORGETFUL

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

Deny destructive operations
{
  "delete_code_artifact": {
    "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
{
  "link_memories": {
    "limits": [
      {
        "counter": "link_memories_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
{
  "get_code_artifact": {
    "limits": [
      {
        "counter": "get_code_artifact_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 Forgetful — 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 FORGETFUL →

Free to start. No card required.

ALL 59 FORGETFUL TOOLS

DESTRUCTIVE 7 tools
Destructive delete_code_artifact Delete code artifact (cascades memory associations). WHEN: Removing obsolete, incorrect, or no-longer Destructive delete_document Delete document (cascades memory associations). WHEN: Removing obsolete, incorrect, or no-longer-rele Destructive delete_entity Delete entity (cascade removes memory links and relationships). WHEN: Removing obsolete or incorrect Destructive delete_entity_relationship Delete entity relationship (removes knowledge graph edge). WHEN: Removing obsolete or incorrect relat Destructive delete_project delete_project Destructive delete_skill Delete skill (cascades memory and artifact associations). WHAT: Permanently removes a skill and its a Destructive mark_memory_obsolete Mark a memory as obsolete (soft delete for audit trail) WHEN: Memory is outdated, contradicted by new
EXECUTE 2 tools
Execute execute_forgetful_tool Placeholder - set dynamically below Execute rebuild_embeddings Rebuild embeddings for a user-scoped subset of memories (issue 39). WHEN: A small set of memories, a
WRITE 29 tools
Write link_memories Manually create bidirectional links between memories WHEN: You or the user decide that a memory wants Write create_code_artifact create_code_artifact Write create_document create_document Write create_entity create_entity Write create_entity_relationship create_entity_relationship Write create_memory create_memory Write create_project create_project Write create_skill create_skill Write import_skill import_skill Write link_entity_to_memory Link entity to memory (establishes reference relationship). WHEN: When a memory mentions or relates t Write link_entity_to_project Link entity to project (organizational grouping). WHEN: When an entity belongs to or is relevant to a Write link_skill_to_code_artifact Link skill to code artifact (establishes reference relationship). WHAT: Creates an association betwee Write link_skill_to_document Link skill to document (establishes reference relationship). WHAT: Creates an association between a s Write link_skill_to_file Link skill to file (establishes reference relationship). WHAT: Creates an association between a skill Write link_skill_to_memory Link skill to memory (establishes reference relationship). WHAT: Creates a bidirectional association Write unlink_entity_from_memory Unlink entity from memory (removes reference relationship). WHEN: When an entity-memory link is no lo Write unlink_entity_from_project Unlink entity from project (removes organizational grouping). WHEN: When an entity-project associatio Write unlink_skill_from_code_artifact Unlink skill from code artifact (removes reference relationship). WHAT: Removes the association betwe Write unlink_skill_from_document Unlink skill from document (removes reference relationship). WHAT: Removes the association between a Write unlink_skill_from_file Unlink skill from file (removes reference relationship). WHAT: Removes the association between a skil Write unlink_skill_from_memory Unlink skill from memory (removes reference relationship). WHAT: Removes the association between a sk Write update_code_artifact update_code_artifact Write update_document update_document Write update_entity update_entity Write update_entity_relationship Update entity relationship (PATCH semantics - only provided fields changed). WHEN: Refining relations Write update_memory update_memory Write update_project update_project Write update_skill update_skill Write update_user_notes Update the notes field for the current user WHAT: Updates the notes/metadata field for the authentica
READ 21 tools
Read get_code_artifact Retrieve code artifact by ID with complete details. WHEN: You need the full code implementation and m Read get_current_user Returns information about the current user WHAT: Returns information about the current authenticated Read get_document Retrieve document by ID with complete content. WHEN: You need the full document content and metadata Read get_entity Retrieve entity by ID with complete details. WHEN: You need the full entity information for a specifi Read get_entity_memories get_entity_memories Read get_entity_relationships get_entity_relationships Read get_memory Retreive complete memory details by ID WHEN: You require the full details of a specific memory and yo Read get_project get_project Read get_recent_memories Retrieve most recent memories by creation timestamp WHEN: You want to see what was recently learned, Read get_skill Retrieve skill by ID with complete content. WHAT: Returns the full skill including markdown content, Read how_to_use_forgetful_tool Get detailed documentation for a specific tool Returns complete documentation including JSON schema, Read list_code_artifacts list_code_artifacts Read list_documents list_documents Read list_entities List entities with optional filtering. WHEN: Browsing entities, filtering by project/type/tags, or di Read list_projects list_projects Read list_skills list_skills Read query_memory query_memory Read search_entities search_entities Read search_skills search_skills Read discover_forgetful_tools Placeholder - set dynamically below Read export_skill Export a skill to Agent Skills markdown format (SKILL.md). WHAT: Generates a standards-compliant SKIL

RELATED SERVERS

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

BNB Chain MCP 1240 tools
adminautomation
Binance MCP Server 734 tools
adminautomation
Nodebench 724 tools
adminautomation
GoHighLevel MCP Server 566 tools
adminautomation
UnClick 451 tools
adminautomation
NowAIKit — ServiceNow AI Toolkit 446 tools
adminautomation
Mcp Windows 441 tools
adminautomation
0nmcp 407 tools
adminautomation

FAQ

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

Yes. The Forgetful server exposes 7 destructive tools including delete_code_artifact, delete_document, delete_entity. 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 Forgetful? +

The Forgetful server has 29 write tools including link_memories, create_code_artifact, create_document. 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 Forgetful.

How many tools does the Forgetful MCP server expose? +

59 tools across 4 categories: Destructive, Execute, Read, Write. 21 are read-only. 38 can modify, create, or delete data.

How do I enforce a policy on Forgetful? +

Register the Forgetful 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 Forgetful tool call.

Deterministic rules across all 59 Forgetful tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON FORGETFUL →

Free to start. No card required.

59 Forgetful tools catalogued and risk-classified — across an index of 42,500+ 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.