Context Dev

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

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

Last updated:

1 can modify or destroy data
1 read-only
2 tools total
Read (1) Write / Execute (1) Destructive / Financial (0)

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

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

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

EXECUTE 1 tools
READ 1 tools
Is the Context Dev MCP server safe to use without restrictions? +

The Context Dev server is primarily read-only with 1 read tools. While it cannot modify data, an agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up costs. Rate limiting is still recommended.

How many tools does the Context Dev MCP server expose? +

2 tools across 2 categories: Execute, Read. 1 are read-only. 1 can modify, create, or delete data.

How do I add Intercept to my Context Dev setup? +

One line change. Instead of running the Context Dev server directly, prefix it with Intercept: intercept -c context-dev.yaml -- npx -y @context.dev-mcp. Download a pre-built policy from policylayer.com/policies/context-dev 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.

Let agents act without letting them run wild.

Deterministic policy on every MCP tool call. Per-identity grants. Full audit log.

// GET IN TOUCH

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

Message sent.

We'll get back to you soon.