Local-first knowledge graph for token-efficient code review through MCP and CLI
Nothing to run from here
TeamCity CI/CD is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
100/100
trust score
29
tools declared
local
runs on your machine
—
downloads a day
What it does
Read-only MCP server for JetBrains TeamCity — builds, configs, logs, tests, agents
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'TEAMCITY_BASE_URL=${TEAMCITY_BASE_URL}' --env 'TEAMCITY_TOKEN=${TEAMCITY_TOKEN}' --transport stdio teamcity-ci-cd-mcp '--' uvx readonly-mcp-teamcity
# 2 — ask your agent for something these tools do
# search_builds, get_build_details, get_build_statistics and 26 more
It needs TEAMCITY_BASE_URL, TEAMCITY_TOKEN: this reads them from your environment, so export them first.
TeamCity CI/CD costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DEAll 2 servers
desty2k2 servers
2 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts TeamCity CI/CD as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads TEAMCITY_BASE_URL (TeamCity server base URL (e.g., https://teamcity.example.com)), TEAMCITY_TOKEN (TeamCity REST API bearer token (scope it read-only)) from your environment each time it starts the server, so the value stays out of its config: export them in your shell profile (macOS, Linux), or run setx TEAMCITY_BASE_URL …, setx TEAMCITY_TOKEN … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'TEAMCITY_BASE_URL=${TEAMCITY_BASE_URL}' --env 'TEAMCITY_TOKEN=${TEAMCITY_TOKEN}' --transport stdio teamcity-ci-cd-mcp '--' uvx readonly-mcp-teamcityReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
It reaches a system of yours, so it needs your own credential rather than the publisher’s: TEAMCITY_BASE_URL — TeamCity server base URL (e.g., https://teamcity.example.com); TEAMCITY_TOKEN — TeamCity REST API bearer token (scope it read-only). You set them in your own client’s config, on your machine — this marketplace never holds it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
29 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Search build history with filters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_type_id | string | no | Filter by build configuration ID. Use this to get history for a specific pipeline. |
| project_id | string | no | Filter by project ID. Returns builds from all configurations in the project. |
| status | string | no | Filter by build status: 'SUCCESS', 'FAILURE', or 'ERROR'. Omit to return all statuses. |
| branch | string | no | Filter by branch name. Use '<default>' for the default branch. Omit to return builds from all branches. |
| running | boolean | no | Filter by running state. True = only running builds, False = only finished, None = all builds. |
| tag | string | no | Filter by build tag (exact match) |
| since_date | string | no | — |
| until_date | string | no | Only builds that finished before this date. Same format as since_date. |
| build_number | string | no | — |
| personal | boolean | no | Filter personal builds. True = only personal, False = exclude personal, None = all. |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Get comprehensive details of a single build.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID — the internal ID, not the build number. |
Get statistical metrics for a build.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
Traverse a build's snapshot-dependency chain.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| direction | string | no | — |
Search TeamCity build agents.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pool_id | integer | no | Filter by agent pool ID. |
| connected | boolean | no | Filter by connection state. True = connected, False = disconnected. |
| authorized | boolean | no | Filter by authorization state. Unauthorized agents cannot run builds. |
| enabled | boolean | no | Filter by enabled state. Disabled agents are excluded from build assignment. |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
List TeamCity agent pools.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Get detailed status for a single build agent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agent_id | integer | yes | Agent ID |
List the artifacts a build produced (one directory level).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| path | string | no | Artifact directory to list (e.g. 'reports'). Empty lists the root. |
Read the text content of a build artifact, paginated by line.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| path | string | yes | Artifact path, e.g. 'reports/junit.xml'. |
| start_line | integer | no | First line to return (0-indexed). |
| max_lines | integer | no | Maximum lines to return. |
| max_line_length | integer | no | Maximum characters per line; longer lines are truncated. |
Search TeamCity build configurations (jobs/pipelines) by structured filters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | Filter by project ID. Returns only build configurations belonging to this project. |
| build_type_id | string | no | Filter by exact build type ID (e.g., 'MyProject_Build'). Use when you know the exact identifier. |
| paused | boolean | no | Filter by paused state. None = all. |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Get full details of a build configuration including steps, triggers, and parameters.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_type_id | string | yes | Build configuration ID (e.g., 'MyProject_Build'). |
List branches available for a build configuration.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_type_id | string | yes | Build configuration ID |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Retrieve build log content, paginated by line.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| start_line | integer | no | Start reading from this line (0-indexed). Omit to start at the beginning. |
| end_line | integer | no | Stop reading at this line (exclusive). At most max_lines lines are returned even if the range is wider. |
| max_lines | integer | no | Maximum number of lines to return (capped at 5000). |
| tail | boolean | no | Return the last lines instead of the first — use when investigating failures. |
Search within a build log for specific text.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| query | string | yes | Text to find in the build log (case-insensitive). |
| context_lines | integer | no | Lines of context to show around each match. |
| max_matches | integer | no | Maximum number of matches to return. |
Search VCS changes (commits) tracked by TeamCity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | no | Get VCS changes included in a specific build. |
| build_type_id | string | no | Get pending changes for a build configuration. |
| project_id | string | no | Get changes across all build configurations in a project. |
| username | string | no | Filter changes by VCS username (committer). |
| since_change | string | no | Only changes after this one: a TeamCity change ID (e.g. '1234') or a full commit SHA. |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Get detailed information about a VCS change including modified files.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| change_id | string | yes | Change ID |
Explain why a build failed, in one call.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| max_failed_tests | integer | no | Failed tests to include |
| max_log_matches | integer | no | Error log lines to include |
| context_lines | integer | no | Log lines of context around each match |
Find build configurations by fuzzy name/project matching.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Free-text query — partial names, project-path fragments, or abbreviations. |
| limit | integer | no | Maximum results to return |
Get problems detected in a build.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Search active investigations in TeamCity.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | Filter investigations by project ID. |
| build_type_id | string | no | Filter investigations by build configuration ID. |
| assignee | string | no | Filter by assignee username. |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
List currently muted tests.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | Filter mutes by project ID. |
| build_type_id | string | no | Filter mutes by build configuration ID. |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Search TeamCity projects by name, ID, or parent.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | no | Filter by project name (case-insensitive exact match) |
| project_id | string | no | — |
| parent_project_id | string | no | Filter to direct children of this parent project ID. Use '_Root' for top-level projects. |
| archived | boolean | no | Include archived projects |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Get detailed information about a single TeamCity project.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | yes | Project ID (e.g., 'MyProject'). |
List builds currently in the TeamCity build queue.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| project_id | string | no | Filter queued builds by project ID. |
| build_type_id | string | no | Filter queued builds by build configuration ID. |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Get TeamCity server version and status information.
Takes no parameters.
Get server health items and runtime metrics.
Takes no parameters.
Get test results for a build.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build_id | string | yes | Numeric build ID |
| status | string | no | — |
| page | integer | no | Page number, 1-indexed |
| limit | integer | no | Max results per page |
Get detailed information about a specific test occurrence.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| test_locator | string | yes | Test occurrence locator (the 'id' field of a test occurrence). |
Parse a TeamCity web URL and extract entity identifiers.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| url | string | yes | — |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install TeamCity CI/CD or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 100 / 100
Release 1.0.1 · scanned 3 Nov 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score100
Findings0 threat · 0 capability
Capabilityminimal
Coveragesource
Verificationsource
Surface digestd56231e3d9a5fbdac28428319b5a84a743cfa57f510d934155dd86b44d713d14
Score vectorthreat 100 → client 100
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (29 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| search_agents | no tags | |
| list_agent_pools | no tags | |
| get_agent_details | no tags | |
| list_build_artifacts | untrusted-input | untrusted-input: keyword "browse" |
| get_build_artifact_content | no tags | |
| search_build_configs | no tags | |
| get_build_config_details | no tags | |
| get_build_config_branches | no tags | |
| get_build_log | no tags | |
| search_build_log | no tags | |
| search_builds | no tags | |
| get_build_details | no tags | |
| get_build_statistics | no tags | |
| get_build_chain | no tags | |
| search_changes | no tags | |
| get_change_details | no tags | |
| diagnose_build | no tags | |
| find_build_config | no tags | |
| get_build_problems | no tags | |
| search_investigations | no tags | |
| list_muted_tests | no tags | |
| search_projects | no tags | |
| get_project_details | no tags | |
| get_build_queue | no tags | |
| get_server_info | no tags | |
| get_server_health | no tags | |
| get_build_test_results | no tags | |
| get_test_details | no tags | |
| resolve_teamcity_url | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digestd56231e3d9a5fbda
Scanned2026-11-03
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 1.0.1. Pin a release below and the command asks for exactly that one.
1.0.1
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish TeamCity CI/CD can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.