90trust / 100

Stigmer

by stigmer.network in Onchain & crypto

MCP serverPassing, checked 21 min ago

Execution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization.

https://stigmer.network/mcp

Last 30 days

All checks passedSome failedAll failedNot checked
Uptime
100%
Response time
178 ms typical, 178 ms slowest 5%
Last check
21 min ago
Next check
in 5 h

How to call it

Add it to any MCP client that supports remote servers.

{
  "mcpServers": {
    "stigmer": {
      "type": "http",
      "url": "https://stigmer.network/mcp"
    }
  }
}

8 tools

  • query

    Search for verified method contracts for any library. Pass any text -- library name, method, what you're building, or an error you hit.

  • list_services

    List all libraries and services that have verified method contracts. Use this first to discover what's available, then query for specific methods.

  • list_methods

    List all methods for a given library or service. Use after list_services to drill into a specific one.

  • policy

    Generate a least-privilege IAM policy for an AWS workflow. Pass a named workflow, explicit IAM actions, or a description. Returns the exact policy with confidence tier and any unresolved operations.

  • list_workflows

    List the curated named workflows that can generate least-privilege IAM policies.

  • verify

    Feed a generated policy back to AWS's own policy evaluation engine (SimulateCustomPolicy) and confirm it grants exactly the intended operations and nothing extra. Returns verified (True|False|unknown), grants_all, grants_extra. Requires AWS credentials; without them verified=unkn

  • authorize

    Pre-flight authorization check for an AWS operation. Resolves the IAM actions the operation requires, then asks AWS's own policy simulator (SimulatePrincipalPolicy) whether the current role (or a given principal) allows them. Returns resolution (exact|partial|unresolved) and eval

  • register

    Register a fix. Three actions: confirm (it worked), append_thread (variant worked), new_receipt (nothing matched, I fixed it).

Security scan

  • No findings. We scan names, descriptions and tool definitions for hidden instructions and other prompt-injection patterns.

Recent checks

WhenResultHTTPTime
21 min agoPassed200239 ms
10 h agoPassed200178 ms