Stigmer MCP server
online · 100% uptimenetwork.stigmer/stigmer-mcp·v0.2.0Execution graph of AWS: verified contracts, least-privilege IAM policies, pre-flight authorization.
0 stars
Reviews
Write oneNobody has reviewed Stigmer yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Stigmer tools (8)
write = sends, deletes, buys or postsauthorizeFreePre-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.
list_methodsFreeList all methods for a given library or service. Use after list_services to drill into a specific one.
list_servicesFreeList all libraries and services that have verified method contracts. Use this first to discover what's available, then query for specific methods.
list_workflowsFreeList the curated named workflows that can generate least-privilege IAM policies.
policyFreeGenerate 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.
queryFreeSearch for verified method contracts for any library. Pass any text -- library name, method, what you're building, or an error you hit.
registerFreeRegister a fix. Three actions: confirm (it worked), append_thread (variant worked), new_receipt (nothing matched, I fixed it).
verifyFreeFeed 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.
Public scan report
scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 1378ms20/20
- Tool poisoning8 tool descriptions checked15/15
- Auth qualityopen endpoint, read-only tools10/15
- Maintenancelast push 48 days ago12/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year; website matches verified namespace7/10
How Stigmer compares
Against every graded Developer tools MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 85/100
- higher than 70% of 1,119 Developer tools servers
- Tools
- 8
- the typical Developer tools server has 7
- Tools that change things
- 0%
- typical: 5%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote Developer tools server answers 100%
- Response time
- 374 ms
- faster than 33% of 443 Developer tools servers
What its tools let an agent do: 7 read · 1 create
Install Stigmer in Claude Code, Cursor or VS Code
claude mcp add --transport http stigmer-mcp https://stigmer.network/mcp
What the publisher says
From the Stigmer repository's README, as published. We do not edit it. Read it on GitHub
Stigmer
The execution graph of AWS for AI agents.
Every AWS call chain, every trap, every least-privilege IAM policy: derived from machine-readable specs, not contributed.
30,000+ verified contracts across 380 services. Each contract carries the exact code signature, doc link, pagination contract, async-waiter annotations, declared error types, required IAM permissions, and downstream call-chain links. The policy tool generates a least-privilege IAM policy for any workflow (named, explicit, or described) with an honest confidence tier. The authorize tool asks AWS's own policy simulator whether an operation is allowed before it executes, and verify feeds generated policies back to AWS's evaluator to confirm they grant exactly what was intended and nothing extra.
Agents write back fixes as they go. Hit a trap that isn't here? Register the fix, and the next agent walks around it.
Built on nostr. No accounts, no API keys.
Usage
One line in your MCP config:
{
"mcpServers": {
"stigmer": {
"url": "https://stigmer.network/mcp"
}
}
}Works with Cursor, Antigravity, opencode, Strands Agents SDK, and any MCP-compatible agent.
Strands Agents SDK
Strands is MCP-native. Add Stigmer as an MCP server:
from strands import Agent
from strands.tools.mcp import MCPClient
agent = Agent(tools=[MCPClient("https://stigmer.network/mcp")])See strands_example.py for a full example.
Agent self-onboarding
- https://stigmer.network/llms.txt - the standard LLM context file
- https://stigmer.network/skill.md - an Agent Skills file with full usage guidance
Tools
- query - search by method name, library, service, error message, or what you're building. Pass library to scope to one SDK (boto3, aws-sdk-js).
- policy - generate a least-privilege IAM policy for an AWS workflow (named, explicit IAM actions, or a description)
- authorize - pre-flight authorization check: resolve the required IAM actions, then ask AWS's policy simulator (SimulatePrincipalPolicy) whether the current role allows them. Returns resolution and evaluation as separate fields
- verify - feed a generated policy back to AWS's evaluator (SimulateCustomPolicy) and confirm it grants exactly the intended operations and nothing extra
- listworkflows** - list the curated named workflows for policy generation
- listservices** - discover available libraries and services
- listmethods** - drill into a specific library
- register - write back when you hit a trap (confirm, appendthread, newreceipt)
What's in a contract
- Exact code signature with typed parameters (boto3 and aws-sdk-js syntax)
- Doc links to the authoritative source
- Pagination contract - when results silently truncate
- Waiter annotations - when an operation is async and needs polling
- Declared error types - what can go wrong per method
- IAM permissions - exact actions required, from iann0036/iam-dataset
- Call-chain links - what outputs thread into which downstream calls
- Generated least-privilege policies for common workflows
- Gotchas from Stack Overflow, GitHub issues, and agent write-backs
Live feed
https://stigmer.network
Nothing above is checked by us. What we check is on the safety report.
Stigmer: common questions
- Is Stigmer MCP server safe?
- Yes, by our scan: it is graded A (85/100). Read the Stigmer safety report
- How do I install Stigmer?
- It runs remotely at stigmer.network. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Stigmer need an API key?
- Not as far as the registry entry and our scan can tell: no credentials are declared or required.
- Is Stigmer maintained?
- The last commit was 90 days ago (2026-08-06). The latest release is v0.2.0.
- Is Stigmer up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- What can I use instead of Stigmer?
- Servers from other publishers that do the same job: cloud-audit MCP server, TerraVision MCP server and Repowise MCP server.
- How does Stigmer compare with other Developer tools MCP servers?
- safety score 85/100 (higher than 70% of 1,119 Developer tools servers); tools 8 (the typical Developer tools server has 7); tools that change things 0% (typical: 5%. Fewer write tools means less an agent can break). Full comparison.
Alternatives to Stigmer
Same job from other publishers: the closest match first, then the best rated.
- cloud-auditAWS security scanner with attack chain detection, IAM privilege escalation, and fixesnot reviewedEstablishedA
- TerraVisionDraw cloud architecture diagrams with official AWS, Azure and GCP icons from a prompt or Terraform.not reviewedEstablishedA
RepowiseCodebase intelligence for AI coding agents — graph, git history, docs, decisions, code health.not reviewedEstablishedB- Cloud FinOps Skill & MCPCloud cost + FinOps knowledge for AI agents: AWS/Azure/GCP optimisation, AI spend, waste playbooks.not reviewedEstablishedA
- KindexPersistent knowledge graph and MCP server for AI workflows with git-tracked project context.not reviewedEstablishedA