// SCAN REPORT

Augments

8 tools. 0 can modify or destroy data without limits.

Read-only server. Low risk, but rate limits prevent runaway API costs.

Last updated:

0 can modify or destroy data
8 read-only
8 tools total
// TOOL MAP
Read (8) Write / Execute (0) Destructive / Financial (0)
// WHAT CAN GO WRONG
✕

Even read-only tools carry cost. An agent in a retry loop can make thousands of API calls per minute, exhausting rate limits and running up bills.

// RECOMMENDED RULES
Cap read operations
compare_packages:
  rules:
    - rate_limit: 60/minute

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

// ALL 8 AUGMENTS TOOLS
READ 8 tools
Read compare_packages Read diagnose_error Read diagnostics Read get_api_context Read get_migration_guide Read get_version_info Read scan_project_deps Read search_apis
// FAQ
Is the Augments MCP server safe to use without restrictions? +

The Augments server is primarily read-only with 8 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 Augments MCP server expose? +

8 tools across 1 categories: Read. 8 are read-only. 0 can modify, create, or delete data.

How do I add Intercept to my Augments setup? +

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

Let agents act without letting them run wild.

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

GET STARTED →
// GET IN TOUCH

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

Message sent.

We'll get back to you soon.