// SCAN REPORT

Claude Session MCP

5 tools. 1 can modify or destroy data without limits.

1 write tool that can modify data. Rate limits recommended.

Last updated: 3 Jul 2026

1 can modify or destroy data

4 read-only

5 tools total

Community server · catalogue entry verified 03/07/2026

How to control Claude Session MCP ↓

TOOL MAP

What Claude Session MCP exposes to your agents

Read (4) Write / Execute (1) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Claude Session MCP tools

Write · Medium sync_planning_doc The tool creates or modifies data (planning documentation and task status) without permanent deletion.

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

POLICY

How to control Claude Session MCP

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

Rate limit write operations

{
  "sync_planning_doc": {
    "limits": [
      {
        "counter": "sync_planning_doc_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "check_context_budget": {
    "limits": [
      {
        "counter": "check_context_budget_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 Claude Session MCP — 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 CLAUDE SESSION →

Instant setup, no code required.

FULL CATALOGUE

All 5 Claude Session MCP tools

WRITE 1 tools

Write sync_planning_doc Update .context/dev/{branch}/ planning documents. Can append to progress log, update active work, or mark task

READ 4 tools

Read check_context_budget Check current context window usage and remaining capacity. Returns tokens used, remaining, percentage, and sta Read get_session_history Get what has been accomplished this session - completed todos, files modified, tool calls, git commits. Read get_session_state Get unified snapshot of current session state including todos, git status, context files, and session info. Read should_reset_context Get intelligent recommendation on whether to reset context. Analyzes context usage, todo completion, git state

EXPLORE

Related servers

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

FAQ

Questions about Claude Session MCP

How do I prevent bulk modifications through Claude Session MCP? +

The Claude Session MCP server has 1 write tools including sync_planning_doc. 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 Claude Session MCP.

How many tools does the Claude Session MCP server expose? +

5 tools across 3 categories: Destructive, Read, Write. 4 are read-only. 1 can modify, create, or delete data.

How do I enforce a policy on Claude Session MCP? +

Register the Claude Session 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 Claude Session MCP tool call.

Deterministic rules across all 5 Claude Session MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON CLAUDE SESSION →

Instant setup, no code required.

5 Claude Session MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.