// SCAN REPORT

Mcp Flow

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

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

Last updated: 2 Jul 2026

6 can modify or destroy data

5 read-only

11 tools total

Community server · catalogue entry verified 02/07/2026

How to control Mcp Flow ↓

TOOL MAP

What Mcp Flow exposes to your agents

Read (5) Write / Execute (6) Destructive / Financial (0)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

High Risk

The most dangerous Mcp Flow tools

Execute · High fix_loop This tool triggers a complex automation loop that runs project checks (equivalent to executing tests/verification commands), analyzes outputs, and applies patches to code. Execute · High run_project_checks The tool runs project checks/tests, which involves executing code external to the MCP server—a classic Execute category action. Write · High apply_patch apply_patch modifies project files by applying diffs, making it a Write operation (creates or modifies data reversibly). Write · Medium create_change_plan This tool creates new data (a change plan) but does not execute code, delete files, or move money.

6 of Mcp Flow's 11 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Mcp Flow

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

Rate limit write operations

{
  "apply_patch": {
    "limits": [
      {
        "counter": "apply_patch_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analyze_check_failures": {
    "limits": [
      {
        "counter": "analyze_check_failures_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 Mcp Flow — 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 MCP FLOW →

Instant setup, no code required.

FULL CATALOGUE

All 11 Mcp Flow tools

EXECUTE 2 tools

Execute fix_loop Run a controlled verify→analyze→fix loop. Each iteration runs the Execute run_project_checks Auto-detect and run the project

WRITE 4 tools

Write apply_patch Apply a unified diff to the project. Defaults to dryRun=true. All Write create_change_plan Assemble a structured change plan from deterministic project context Write generate_patch Turn concrete Write generate_project_doc Scan a project and write a compact project.md (structure, stack,

READ 5 tools

Read analyze_check_failures Parse test / lint / typecheck / build output into structured issues Read git_status Report the Git state: current branch, staged/modified/untracked Read inspect_project Analyze a project Read read_relevant_files Read the files most relevant to a task without loading the whole Read summarize_changes Produce a clean summary of changes: a user-facing summary, a technical

EXPLORE

Related servers

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

FAQ

Questions about Mcp Flow

How do I prevent bulk modifications through Mcp Flow? +

The Mcp Flow server has 4 write tools including apply_patch, create_change_plan, generate_patch. 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 Mcp Flow.

How many tools does the Mcp Flow MCP server expose? +

11 tools across 3 categories: Execute, Read, Write. 5 are read-only. 6 can modify, create, or delete data.

How do I enforce a policy on Mcp Flow? +

Register the Mcp Flow 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 Mcp Flow tool call.

Deterministic rules across all 11 Mcp Flow tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MCP FLOW →

Instant setup, no code required.

11 Mcp Flow tools catalogued and risk-classified — across an index of 43,000+ MCP servers.