// SCAN REPORT

Anchor

6 tools. 6 can modify or destroy data without limits.

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

Last updated: 3 Jul 2026

6 can modify or destroy data

0 read-only

6 tools total

Community server · catalogue entry verified 03/07/2026

How to control Anchor ↓

TOOL MAP

What Anchor exposes to your agents

Read (0) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Anchor tools

Write · Medium memory_manager The memory_manager tool creates and stores new memories/decisions in persistent state, which is a reversible data modification operation (Write). Write · Medium notepad_manager This tool modifies persistent working state by saving and updating notepads. Write · Medium plan_manager The tool performs both read and write operations on plan data. Write · Medium promote_learning The tool creates or modifies data (appending to rules.md) in a reversible manner.

6 of Anchor's 6 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Anchor

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

Rate limit write operations

{
  "memory_manager": {
    "limits": [
      {
        "counter": "memory_manager_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Create a free account and register Anchor — 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 ANCHOR →

Instant setup, no code required.

FULL CATALOGUE

All 6 Anchor tools

WRITE 6 tools

Write memory_manager Manage memory: add a learning/decision, search memories, or list recent memories. Write notepad_manager Manage notepads: read a notepad by topic, save/update a notepad, or list all topics. Write plan_manager Manage plans: read a plan, save/update a plan, or list all plan names. Write promote_learning Promote learnings from a plan into project rules. Appends plan learnings to rules.md. Write rules_manager Manage project rules: read current rules or save/update rules. Write task_manager Manage tasks: get active task, set a new active task, complete a task, or list all tasks.

FAQ

Questions about Anchor

How do I prevent bulk modifications through Anchor? +

The Anchor server has 6 write tools including memory_manager, notepad_manager, plan_manager. 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 Anchor.

How many tools does the Anchor MCP server expose? +

6 tools across 1 categories: Write. 0 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Anchor? +

Register the Anchor 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 Anchor tool call.

Deterministic rules across all 6 Anchor tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON ANCHOR →

Instant setup, no code required.

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