Flowforge

49 tools. 26 can modify or destroy data without limits.

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

Last updated:

26 can modify or destroy data
23 read-only
49 tools total
Read (23) Write / Execute (20) Destructive / Financial (6)

Destructive tools (flowforge_cancel_run, flowforge_delete_credential, flowforge_delete_function) permanently delete resources. There is no undo. An agent calling these in a retry loop causes irreversible damage.

Write operations (flowforge_add_comment, flowforge_approve_tool_call, flowforge_create_agent) modify state. Without rate limits, an agent can make hundreds of changes in seconds — faster than any human can review or revert.

Execute tools (flowforge_replay_run, flowforge_retry_run) trigger processes with side effects. Builds, notifications, workflows — all fired without throttling.

One command. Full control.

Intercept sits between your agent and Flowforge. Every tool call checked against your policy before it executes — so your agent can do its job without breaking things.

npx -y @policylayer/intercept scan -- npx -y @flowforge-mcp-server
Scans every tool. Generates a policy. Starts enforcing.
Works with Claude Code · Cursor · Claude Desktop · Windsurf · any MCP client
Deny destructive operations
flowforge_cancel_run:
  rules:
    - action: deny

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations
flowforge_add_comment:
  rules:
    - rate_limit: 30/hour

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations
flowforge_get_agent:
  rules:
    - rate_limit: 60/minute

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

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

Yes. The Flowforge server exposes 6 destructive tools including flowforge_cancel_run, flowforge_delete_credential, flowforge_delete_function. These permanently remove resources with no undo. Intercept blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Flowforge? +

The Flowforge server has 18 write tools including flowforge_add_comment, flowforge_approve_tool_call, flowforge_create_agent. Set rate limits in your policy file -- for example, rate_limit: 10/hour prevents an agent from making more than 10 modifications per hour. Intercept enforces this at the transport layer.

How many tools does the Flowforge MCP server expose? +

49 tools across 4 categories: Destructive, Execute, Read, Write. 23 are read-only. 26 can modify, create, or delete data.

How do I add Intercept to my Flowforge setup? +

One line change. Instead of running the Flowforge server directly, prefix it with Intercept: intercept -c flowforge.yaml -- npx -y @flowforge-mcp-server. Download a pre-built policy from policylayer.com/policies/flowforge and adjust the limits to match your use case.

Other MCP servers with similar tools.

Starter policies available for each. Same risk classification, same one-command setup.

policylayer/intercept

Control every MCP tool call
your agent makes.

Set budgets, approvals, and hard limits across MCP servers.

npx -y @policylayer/intercept init
Protect your agent in 30 seconds. Scans your MCP config and generates enforcement policies for every server.
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.