MCP.Market

Cirdan MCP server

by adanb13·io.github.adanb13/cirdan·v0.9.0
No reviews yet

AI infrastructure cartographer & MCP server: fingerprints, graphs & watches live infra for agents

B72/100grade B
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
B72/100

full report

Adoption
Growing

0 stars82 downloads/wk

Reviews

Write one

Nobody has reviewed Cirdan yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Cirdan tools (29, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • annotate_node

    Attach evidence or attributes to an existing node without changing its confidence.

  • describe_node

    Restart/impact for one node in a single call: node summary plus what is affected if it goes down (dependents/blast radius) and what must be healthy first (dependencies/prerequisites). `node_id` is an alias for `node_ref`.

  • describe_system

    One-shot system overview: runtime/cloud, services + their dependencies, hubs, and public entry points.

  • execute_actionwrite action

    Execute an action id from list_available_actions. Recorded, redacted, audited.

  • explain_incident

    Evidence-backed markdown explanation of an incident.

  • fingerprint_system

    Detect runtimes, clouds, IaC, and telemetry with confidence and evidence.

  • generate_report

    Regenerate INFRA_REPORT.md and return its contents.

  • generate_view

    Generate an Agentic UI view ('show me …') and save html/md/json artifacts.

  • get_access_context

    What the current agent/session can access (capability mirror, not permissions).

  • get_audit

    Recent audit entries: what Cirdan observed, generated, executed, verified.

  • get_enrichment_targets

    What the deterministic scanners left unconnected: docs to read, isolated nodes, unlinked IaC, uncertain claims. Contribute findings via upsert_edge.

  • get_logs

    Tail logs for a component through the owning live adapter. `node_id` is an alias for `node_ref`.

  • get_neighbors

    Neighborhood subgraph around a node. `node_id` is an alias for `node_ref`.

  • get_node

    Fetch one node (by id or fuzzy name) with evidence, attributes, and edges. `node_id` is an alias for `node_ref`.

  • get_recent_errors

    Recent error/warning events, clustered by message template.

  • get_state

    Live state of a component through the owning adapter. `node_id` is an alias for `node_ref`.

  • list_available_actions

    Actions currently possible against a component with this session's access. `node_id` is an alias for `node_ref`.

  • list_dependencies

    What a component depends on (transitive). `node_id` is an alias for `node_ref`.

  • list_dependents

    What depends on a component (transitive blast radius). `node_id` is an alias for `node_ref`.

  • list_incidents

    Open (and optionally resolved) incidents. Runs a detection pass by default.

  • list_public_entrypoints

    Everything reachable from outside, with the reasons.

  • list_runtime_workloads

    Current workloads (services, containers, pods, units) with live state.

  • list_services

    All logical services with state and origin.

  • map_infrastructurewrite action

    Run full discovery (static + live) and regenerate all cirdan-out artifacts.

  • query_infra_graph

    Ask the graph a question, e.g. 'what depends on postgres?' or 'what broke?'.

  • shortest_path

    Shortest path between two components.

  • upsert_edge

    Contribute a relationship between existing nodes (ids or names). Evidence required.

  • upsert_node

    Contribute a node the scanners missed. Evidence quotes required; recorded as INFERRED.

  • verify_action

    Verify the outcome of a previously executed action (act-… record id).

Public scan report

scanner v0.1.9 · 2026-09-26 · same rubric, same numbers if you re-run it

2 medium
  • Code scan3 source files scanned; 86 source files scanned15/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 66 days ago12/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10

Findings (2)

  • mediumnpm install lifecycle script presentinstall.script
  • mediumnpm install lifecycle script presentinstall.script
    package.json: … "README.md" ], "scripts": { "postinstall": "node install-check.js || true" }, …
Overall 72/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Cirdan compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
72/100
higher than 38% of 48,255 servers
Tools
29
the typical server has 7
Tools that change things
7%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
82
more than 58% of 12,191 servers with a package

What its tools let an agent do: 25 read · 2 create · 1 change · 1 run or deploy

Install Cirdan in Claude Code, Cursor or VS Code

Runs npx -y @cirdanops/cli on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add cirdan -- npx -y @cirdanops/cli
Add to Cursor

What the publisher says

From the Cirdan repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.adanb13/cirdan -->

Cirdan

Cirdan is an on-call software repair agent. A production alert fires — Grafana, Alertmanager, or Slack. Cirdan resolves the affected service and its repo from the explicit services: registry in cirdan.yaml, reproduces the failure in an isolated runner (Docker Compose or Kubernetes), has a coding agent fix the code — your own logged-in Claude Code / Codex CLI, or an API provider — re-verifies the fix against the pinned reproduction probe and the repo's test suite, and opens a verified pull request. When policy allows, it merges, deploys, and verifies production recovery, stopping at manual_required with full evidence when recovery fails.

alert ─▶ resolve service + repo (the services: registry) ─▶ reproduce in an isolated runner
      ─▶ coding agent fixes the code ─▶ verify (pinned repro probe + sandboxed test suite)
      ─▶ verified PR (@cirdan review loop; CI checks watched) ─▶ optional merge + deploy
      ─▶ verify recovery in production

The job it does: when an alert fires at 3am for a code-shaped failure, a verified fix PR (or a completed deploy plus recovery confirmation) is waiting instead of a page.

Cirdan is deliberately not an infrastructure mapper, a topology explorer, an observability dashboard, a generic agent launcher, or a ChatOps bot. It repairs the services you register — nothing is discovered, and nothing is repaired implicitly.

Quickstart

pipx install "cirdanops[all]"      # or uv / pip / npm / brew / curl / docker — see Install
cirdan setup                       # opens the local, loopback-only setup UI

cirdan setup walks one short path and shows a readiness banner that flips to "Ready to repair" only when this install can actually fix something:

or Use the API (managed credentials + a GitHub App). See Two ways to run.

  1. Choose a pathway — Use the CLI (the tools already logged in on this machine)

intake, or Slack.

  1. Connect an alert source — a Grafana webhook (+ HMAC), native Alertmanager

repos your gh login can push to; pick which ones it may repair. Only selected repositories are ever repaired.

  1. Select repair repositories — in Source Code Connection, Cirdan lists the

real payload you paste) and must show it resolving to a selected repository and routing to a code-repair pipeline.

  1. Prove routing — the Alert routing step synthesizes a sample alert (or takes a
  1. Start the daemon and post a demo alert:
cirdand serve --http
curl -X POST localhost:8090/v1/ingest/grafana -d @examples/demo/alert.firing.json

The runnable demo in examples/demo/ wires this end to end. The same checklist is available headlessly — cirdan status --checks prints the identical table and exits 1 until the install is ready. Useful setup flags:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Cirdan: common questions

Is Cirdan MCP server safe?
Mostly: it is graded B (72/100). Read the Cirdan safety report
How do I install Cirdan?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Cirdan need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is Cirdan maintained?
The last commit was 104 days ago (2026-07-23). The latest release is v0.9.0.
How does Cirdan compare with other MCP servers?
safety score 72/100 (higher than 38% of 48,255 servers); tools 29 (the typical server has 7); tools that change things 7% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.