Gocd MCP server
io.github.Sahilll15/gocd·v0.1.2·1 starsMCP server for GoCD: dashboard, pipelines, artifacts, agents. Context-lean output.
1 stars41 downloads/wk
Reviews
Write oneNobody has reviewed Gocd yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Gocd tools (19)
write = sends, deletes, buys or postsRead from the package source without running it. The installed server may list more.
gocd_compareWhat changed between two pipeline runs: commits per material.
gocd_dashboardDashboard health, context-lean. Default (no args) returns a SUMMARY; pass filter/status/detail to drill down.
gocd_environmentsList environments as [name, pipeline_count, env_vars]. Optional name filter.
gocd_get_agentOne agent's identity and state by uuid.
gocd_get_artifactFetch one artifact file's content (e.g. console.log). Returns at most cap_kb from the END of the file to stay context-lean.
gocd_list_agentsList GoCD build agents (compact rows). Optional filter, limit.
gocd_list_artifactsList the artifact files produced by one pipeline job, as flat [path, url] rows.
gocd_materialsList configured materials as [type, descriptor, fingerprint]. Optional name filter.
gocd_pause_pipelinePause a pipeline.
gocd_pipeline_groupsList pipeline groups. No filter = [group, pipeline_count]; with a filter, lists matching pipeline names (raw config is several MB).
gocd_pipeline_historyRecent run history for one pipeline (compact rows).
gocd_pipeline_instanceOne pipeline run: stages with per-job result, plus trigger. Omit counter for the latest.
gocd_pipeline_statusGet paused/locked/schedulable status for one pipeline.
gocd_server_healthCurrent GoCD server health messages with a count by level.
gocd_stage_historyRecent runs of one stage as compact rows.
gocd_stage_instanceOne stage run with per-job state and the agent each ran on.
gocd_trigger_pipelineSchedule (trigger) a pipeline run.
gocd_unpause_pipelineResume a paused pipeline.
gocd_versionGoCD server version info.
Public scan report
scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it
- Code scan2 source files scanned25/25
- –Live reliabilityno gateway calls yet and no remote to proben/a
- –Tool poisoningtools not inspected (local package is not executed); not countedn/a
- Auth qualitystatic API keys via environment variables6/15
- Maintenancelast push 64 days ago12/15
- Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
How Gocd compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 78/100
- higher than 57% of 48,243 servers
- Tools
- 19
- the typical server has 7
- Tools that change things
- 0%
- typical: 0%. Fewer write tools means less an agent can break
- GitHub stars
- 1
- more than 65% of 28,706 servers
- Downloads a week
- 41
- more than 31% of 12,306 servers with a package
What its tools let an agent do: 19 read
Install Gocd in Claude Code, Cursor or VS Code
Runs npx -y gocd-mcp on your machine. Read the scan report first; the gateway never runs local packages.
claude mcp add gocd -- npx -y gocd-mcp
What the publisher says
From the Gocd repository's README, as published. We do not edit it. Read it on GitHub
gocd-mcp
An MCP server for GoCD. It exposes GoCD's REST API as MCP tools so any MCP client (Claude Code, Claude Desktop, Cursor) can read pipeline state and drive pipelines. Two implementations live here and behave identically on the wire: pick whichever fits how you want to install it.
- go/ — Go implementation. Ships as a single static binary or a Docker image. Fast cold start, low memory.
- ts/ — TypeScript implementation. Runs on Node with no dependencies, so npx needs no build step.
Both return the same context-lean output: the dashboard is summarized by default, rows are column-oriented, and responses are compact JSON. A full GoCD dashboard is several MB across many pipelines; these tools trim it to what the model needs.
Tools
Read tools (safe):
Write tools (operate):
Set GOCDREADONLY=1 to hide the three write tools. Large listings (dashboard, pipelinegroups, materials, environments) are summarized or filterable so they never dump the raw multi-MB body into the model's context.
Configuration
Two environment variables, both required:
GOCD_BASE_URL=https://gocd.example.com
GOCD_ACCESS_TOKEN=<personal access token>GOCDBASEURL is the bare host, without a trailing /go. The tools append /go/api/... themselves. Create the token in GoCD under your profile, Personal Access Tokens.
Install
npx (Node >= 18), recommended
Zero install, nothing to build. This is the simplest way to run the server:
claude mcp add gocd -e GOCD_BASE_URL=... -e GOCD_ACCESS_TOKEN=... -- npx -y gocd-mcpPublished on npm as gocd-mcp and on the MCP Registry as io.github.Sahilll15/gocd, so registry-aware clients can find it by name.
Go binary
Download a prebuilt binary from Releases, or build it:
cd go && go build -o gocd-mcp .Register it:
claude mcp add gocd -e GOCD_BASE_URL=... -e GOCD_ACCESS_TOKEN=... -- /path/to/gocd-mcpDocker
claude mcp add gocd -e GOCD_BASE_URL=... -e GOCD_ACCESS_TOKEN=... \
-- docker run -i --rm -e GOCD_BASE_URL -e GOCD_ACCESS_TOKEN ghcr.io/sahilll15/gocd-mcpTo run the TypeScript source directly during development (Node >= 22.6, uses type-stripping):
cd ts && node --experimental-strip-types src/server.tsWhich one
Shortened. The full README is on GitHub.
Nothing above is checked by us. What we check is on the safety report.
Gocd: common questions
- Is Gocd MCP server safe?
- Mostly: it is graded B (78/100). Read the Gocd safety report
- How do I install Gocd?
- It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
- Does Gocd need an API key?
- Yes. The registry entry asks for
GOCD_ACCESS_TOKEN. - Is Gocd maintained?
- The last commit was 70 days ago (2026-08-27). The latest release is v0.1.2.
- How does Gocd compare with other MCP servers?
- safety score 78/100 (higher than 57% of 48,243 servers); tools 19 (the typical server has 7); tools that change things 0% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.