MCP.Market

MCP server

online · 50% uptime
by mcp.cycloid.io·io.cycloid.mcp/server·v1.0.1

An MCP server that let you interact with Cycloid.io Internal Development Portal and Platform

B79/100grade B
What users say
No reviews yet
Be the first
Safety scan
B79/100

full report

Adoption
New

0 stars

Reviews

Write one

Nobody has reviewed MCP yet.

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

MCP tools (13, 1 write)

write = sends, deletes, buys or posts
  • CYCLOID_BLUEPRINT_LISTFree

    List all available blueprints with their details. The LLM can filter the results based on user requirements.

  • CYCLOID_BLUEPRINT_STACK_CREATEwrite actionFree

    Create a new Cycloid stack from a blueprint. CRITICAL: When elicitation context (ctx) is provided, the tool will ALWAYS use interactive elicitation to ask for parameters one by one, REGARDLESS of any parameters provided. The LLM should ONLY provide the 'ref' parameter and let elicitation handle the rest. DO NOT provide name, use_case, or service_catalog_source_canonical when elicitation is available.

  • CYCLOID_CATALOG_REPO_LISTFree

    List all available service catalog repositories with their details. The LLM can filter the results based on user requirements.

  • CYCLOID_COMPONENT_GETFree

    Get the state of one or more components in a project environment.

  • CYCLOID_COMPONENT_LISTFree

    List components in a project environment.

  • CYCLOID_EVENT_LISTFree

    List organization events with optional filters. To filter by WHAT HAPPENED, use `action` (e.g. create, update, delete, configure, pause, unpause) and/or `entity` (e.g. component, ci_build, ci_job, pipeline, credential) — these are matched case-insensitively against each event's actual `action`/`entity` tag VALUE (note: the entity is `ci_build`, not `build`). If a filter matches nothing while events exist, the response lists the available_actions/available_entities to retry with. `type` is ONLY the high-level category: Cycloid, AWS, Monitoring, Custom (do NOT pass an action/entity name as `type`). `severity` is one of: info, warn, err, crit. `begin`/`end` are Unix timestamps in SECONDS (strings); omit any filter to include all of its values. Returns full event payload including tags. Actor identity is in tags as {key: 'user', value: '<username>'}.

  • CYCLOID_MEMBER_LISTFree

    List all members of the organization. Use this to look up a member's numeric `id` from their `username`. The `id` field is required to build member URLs: /organizations/<org>/members/<id>.

  • CYCLOID_PIPELINE_LISTFree

    List all pipelines from Cycloid.

  • CYCLOID_PROJECT_EVENTSFree

    List events scoped to a specific project's components. Walks project → envs → components, then filters org-wide events by project tag. Returns events, count, and a deduplicated actors list extracted from tags[key=user]. Actor usernames can be cross-referenced with CYCLOID_MEMBER_LIST to get numeric ids for building member URLs. Hard cap: aborts with a structured error if total components exceed the configured maximum (default 50). Use begin/end/severity/type/action/entity to narrow results. Filter by WHAT HAPPENED with `action` (e.g. create, update, delete, configure, pause, unpause) and/or `entity` (e.g. component, ci_build, ci_job, pipeline) — matched case-insensitively against each event's actual tag VALUE (the entity is `ci_build`, not `build`). If a filter matches nothing while events exist, the response lists available_actions/available_entities to retry with. `type` is ONLY the high-level category: Cycloid, AWS, Monitoring, Custom (do NOT pass an action/entity name as `type`). `severity` is one of: info, warn, err, crit.

  • CYCLOID_PROJECT_GETFree

    Get one or more projects by canonical.

  • CYCLOID_PROJECT_LISTFree

    List all projects in the organization.

  • CYCLOID_PROJECT_LIST_ENVFree

    List environments in a project.

  • CYCLOID_STACKFORMS_VALIDATEFree

    Validate a StackForms (.forms.yml) file using the Cycloid CLI. This tool can validate StackForms configuration and provide detailed feedback for fixing issues.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

no findings
  • –Code scanremote-only server, no package to scann/a
  • Live reliabilityremote reachable in 1984ms20/20
  • Tool poisoning13 tool descriptions checked15/15
  • Auth qualityAPI key sent as a header8/15
  • Maintenancelast push 143 days ago8/15
  • Maintainer identityendpoint served from the registry-verified namespace domain8/10
Overall 79/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How MCP compares

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

Safety score
79/100
higher than 58% of 48,255 servers
Tools
13
the typical server has 7
Tools that change things
8%
typical: 0%. Fewer write tools means less an agent can break
Uptime
50%
of our recent checks; the typical remote server answers 100%
Response time
883 ms
faster than 14% of 30,031 servers

What its tools let an agent do: 12 read · 1 change

Install MCP in Claude Code, Cursor or VS Code

claude mcp add --transport http server https://mcp.cycloid.io/mcp
Add to Cursor

Grade history

  • 2026-10-30restoreF → Bscore 79

MCP: common questions

Is MCP server safe?
Mostly: it is graded B (79/100). Read the MCP safety report
How do I install MCP?
It runs remotely at mcp.cycloid.io. 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 MCP need an API key?
Yes. The registry entry asks for X-CY-API-KEY.
Is MCP maintained?
The last commit was 148 days ago (2026-06-09). The latest release is v1.0.1.
Is MCP up?
50% of our last 28 checks got an answer. We check remote servers about four times a day.
How does MCP compare with other MCP servers?
safety score 79/100 (higher than 58% of 48,255 servers); tools 13 (the typical server has 7); tools that change things 8% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.