Stigmer
Server Details
Execution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- Repository
- LNSHRIVAS/stigmer
- GitHub Stars
- 0
- Server Listing
- stigmer
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 8 tools
Each tool targets a distinct part of the workflow: discovery (list_services, list_methods, query), authorization checking (authorize), policy generation (policy), verification (verify), workflow enumeration (list_workflows), and feedback (register). The only potential overlap is authorize vs verify, but the descriptions clearly differentiate pre-flight operation checks from post-generation policy validation.
The list_* prefix is used consistently for the three discovery tools, and the remaining tools are short action verbs (authorize, query, register, verify). The main inconsistency is 'policy', which is a noun rather than a verb, but overall the naming is readable and predictable with minor deviations.
With 8 tools, the server is well-scoped for its purpose—covering discovery, policy generation, verification, authorization, and feedback. Each tool earns its place, and the count is within the ideal range for a focused workflow.
The toolset covers the core lifecycle: discover services/methods, generate least-privilege policies, verify them, authorize operations, and register fixes. A minor gap is the lack of a tool to list or manage registered fixes, but this is not essential to the main workflow and may be intentionally out of scope.
Available Tools
8 toolsauthorizeAInspect
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 evaluation (allowed|denied|unknown) as separate fields. Requires AWS credentials; without them evaluation=unknown with the reason.
Inputs: workflow, operations, principal_arn.
list_methodsAInspect
List all methods for a given library or service. Use after list_services to drill into a specific one.
Inputs: service (required).
list_servicesAInspect
List all libraries and services that have verified method contracts. Use this first to discover what's available, then query for specific methods.
Inputs: no named parameters.
list_workflowsAInspect
List the curated named workflows that can generate least-privilege IAM policies.
Inputs: no named parameters.
policyAInspect
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.
Inputs: workflow, operations, description.
queryBInspect
Search for verified method contracts for any library. Pass any text -- library name, method, what you're building, or an error you hit.
Inputs: sig, limit, query, packages, +1 more.
registerAInspect
Register a fix. Three actions: confirm (it worked), append_thread (variant worked), new_receipt (nothing matched, I fixed it).
Inputs: action (required), symbol (required), library (required), env, +5 more.
verifyAInspect
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=unknown with the reason. Wildcarded operations are expanded to concrete actions first.
Inputs: policy, workflow, operations.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Machine-checkable authority leases for agents: scoped, budgeted, expiring, revocable and audited.
Bounded authorization and independently verifiable execution evidence for agents.
Agent Pay and planning graph for stablecoin commerce.
Machine-verifiable authorization checks for autonomous AI agents.
Related MCP Servers
- AlicenseAqualityBmaintenanceSigned, delegable permissions for AI agents that become the WebAssembly sandbox of each tool call, with a signed, hash-chained receipt per call that anyone can replay. Taint follows the delegation chain to contain prompt injection.4Apache 2.0
- AlicenseCqualityBmaintenancePersistent multi-agent work graph and document-state machine for contracts, specs, slices, evidence, verification, handoffs, and cost-aware AI execution.7Apache 2.0
- AlicenseAqualityBmaintenanceLeast-privilege compiler and MCP gateway for AI agents: run your agent in record-only mode, compile the smallest policy it actually needs from its real tool calls, enforce it at the gateway (deny > approve > allow), and keep a SHA-256 hash-chained audit of every call that verifies offline.141Apache 2.0
- AlicenseNot gradedqualityCmaintenanceEnables autonomous AI governance and pre-action verification for Alexa+ agents, blocking high-risk operations like unlocking doors or financial transactions while grounding decisions in verifiable policy and AWS Bedrock reasoning.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.