Depot MCP by usefulapi is an MCP server with 24 tools an agent can call, among them depot_cache_delete_entries, depot_cache_list_entries, depot_ci_cancel_run. It answers at https://depot.usefulapi.io/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 4 of 4 times since 29 September 2026; the last check, on 15 November 2026, succeeded.
Inspect Depot builds, CI runs, job logs and Actions runners; retry or cancel CI runs.
Description as the publisher wrote it.
| Tool | What it does |
|---|---|
depot_cache_delete_entries | WRITE — deletes cached build data; a later build rebuilds it. Delete Depot Cache entries by exact key. Without confirm it only previews: it shows which keys exist, with their size, and deletes nothing. Show the preview to the user, then cal Inputs: entry_type, keys, confirm |
depot_cache_list_entries | List Depot Cache entries of one type, optionally by key prefix: key, size in bytes, name and creation time (Depot returns no last-access time and no repository). Retention and size limits are set only in the dashboard (Organization Settings Inputs: entry_type, key_prefix, page_size, page_token |
depot_ci_cancel_run | WRITE — stops work in progress. Cancel a queued or running Depot CI run and all of its unfinished workflows, jobs and attempts. Cancelled jobs can be retried afterwards with depot_ci_retry_failed_jobs. Depot: CIService/CancelRun. Inputs: run_id |
depot_ci_get_failure_diagnosis | Get Depot's failure diagnosis for a CI run, workflow, job or attempt. For runs and workflows, identical failures are grouped by error fingerprint; for a job or attempt it is a focused diagnosis with evidence. Empty when no failure evidence Inputs: target_type, target_id |
depot_ci_get_job | Get one Depot CI job: status, conclusion, error message, timestamps, runner config (labels, image, CPUs, memory), matrix values, parent run/workflow context, dependencies and attempt history. Depot: CIService/GetJob. Inputs: job_id |
depot_ci_get_job_logs | Get persisted log lines for a Depot CI job attempt, oldest first (step key/name, timestamp, line number, body). Pass job_id to read the job's latest attempt, or attempt_id for a specific one — exactly one. Pass nextPageToken back as page_to Inputs: job_id, attempt_id, page_token |
depot_ci_get_run_status | Get a Depot CI run's status with its nested workflows, jobs and attempts (ids, keys, statuses, error messages). This is how to find the workflowId / jobId / attemptId for the log, diagnosis and retry tools. Depot: CIService/GetRunStatus. Inputs: run_id |
depot_ci_list_runs | List Depot CI runs, newest first. Filter by status (default: running + queued — pass ["failed"] to find failures), repo, commit SHA prefix, trigger event, or pull request number (requires repo). Depot: CIService/ListRuns. Inputs: status, repo, sha, trigger, pr, page_size |
depot_ci_list_workflows | List Depot CI workflows across runs, newest first, with per-status job counts. Filter by name/path text, repo, status, trigger, SHA prefix or PR number. Depot: CIService/ListWorkflows. Inputs: name, repo, status, trigger, sha, pr |
depot_ci_retry_failed_jobs | WRITE — starts compute. Retry only the failed and cancelled jobs in a Depot CI workflow, plus skipped jobs that depend on them. Jobs that succeeded are left alone. Depot: CIService/RetryFailedJobs. Inputs: workflow_id |
depot_ci_retry_job | WRITE — starts compute. Retry one failed or cancelled Depot CI job, plus any skipped jobs that depend on it. Fails if a dependent job already started; use depot_ci_retry_failed_jobs then. Depot: CIService/RetryJob. Inputs: workflow_id, job_id |
depot_create_project | WRITE. Create a Depot container-build project (an isolated build cache). Idempotent by name: if an active project with the same name exists, that project is returned. Defaults: cache 50 GB / 14 days, hardware HARDWARE_16X32 on AWS builders. Inputs: name, region_id, organization_id, cache_keep_gb, cache_keep_days, hardware |
depot_get_build | Get one container build's status, timestamps, duration, time saved and cached/total step counts. Depot: core BuildService/GetBuild. Inputs: build_id |
depot_get_build_step_logs | Get the log lines (message + timestamp) of one container-build step, identified by its digest from depot_get_build_steps. Depot: build.v1 BuildService/GetBuildStepLogs. Inputs: project_id, build_id, step_digest, page_size, page_token |
depot_get_build_steps | List the BuildKit steps of a container build: name, digest, start/end time, cache state (CACHED / UNCACHED), any error, and whether it has logs. Find the failing step here, then pass its digest to depot_get_build_step_logs. Depot: build.v1 Inputs: project_id, build_id, page_size, page_token |
depot_get_project | Get one Depot project — name, region, hardware size, cache policy, build timeout and autoscaling. Depot: ProjectService/GetProject. Inputs: project_id |
depot_get_usage | Get the organization's Depot usage over a window: container builds per project (build count, minutes saved, minutes billed), GitHub Actions jobs per repo/workflow/runner (minutes elapsed and billed), storage, and agent sandboxes. Depot: Usa Inputs: start_at, end_at |
depot_gha_get_analytics | Get time-bucketed GitHub Actions analytics for Depot runners: job counts (successful/failed/cancelled), failure rate, elapsed and billable seconds, average duration — as totals plus hourly or daily buckets. Defaults to the last 30 days (max Inputs: start_at, end_at, aggregation_unit, repositories, workflows, jobs |
depot_gha_list_jobs | List GitHub Actions jobs that ran on Depot-managed runners, newest first: status, conclusion, runner label, requested CPU/memory, duration, billable time and GitHub URL. Defaults to the last 30 days (max window 90 days). Depot: GithubAction Inputs: repositories, statuses, conclusions, runner_labels, query, start_at |
depot_gha_list_recommendations | List Depot's runner-size recommendations from job CPU and memory metrics: SIZE_UP when average CPU or memory reaches 90%, SIZE_DOWN when both averages stay ≤30% and peaks ≤70%, with current vs suggested size and per-minute price. Defaults t Inputs: start_at, end_at, repositories, workflows, jobs, runner_labels |
depot_gha_search_logs | Search GitHub Actions log lines from Depot runners, newest match first (job, workflow, step, timestamp, body, lineId). Defaults to the last hour (max window 30 days). Filter by repository, workflow, runner label, action or compute id. Depot Inputs: query, start_at, end_at, repositories, workflows, runner_labels |
depot_list_builds | List container builds in a project, newest first: status (STATUS_RUNNING / FAILED / SUCCESS / ERROR / CANCELED), timestamps, build duration, time saved by cache, and cached vs total steps. Depot: core BuildService/ListBuilds. Inputs: project_id, page_size, page_token |
depot_list_projects | List the organization's Depot projects. A project is an isolated container-build cache (region, hardware, cache policy). Use the returned projectId with the build and registry tools. Depot: ProjectService/ListProjects. Inputs: region_id, page_size, page_token |
depot_list_registry_images | List the images stored in a project's Depot Registry: tag, digest, pushedAt and sizeBytes. Depot: build.v1 RegistryService/ListImages. Inputs: project_id, page_size, page_token |
Every block below points at https://depot.usefulapi.io/mcp. Pick your client and copy.
claude mcp add --transport http depot-mcp-by-usefulapi https://depot.usefulapi.io/mcp
{
"mcpServers": {
"depot-mcp-by-usefulapi": {
"command": "npx",
"args": ["-y", "mcp-remote", "https://depot.usefulapi.io/mcp"]
}
}
}{
"mcpServers": {
"depot-mcp-by-usefulapi": {
"url": "https://depot.usefulapi.io/mcp"
}
}
}{
"servers": {
"depot-mcp-by-usefulapi": {
"type": "http",
"url": "https://depot.usefulapi.io/mcp"
}
}
}{
"context_servers": {
"depot-mcp-by-usefulapi": {
"url": "https://depot.usefulapi.io/mcp"
}
}
}{
"mcpServers": {
"depot-mcp-by-usefulapi": {
"serverUrl": "https://depot.usefulapi.io/mcp"
}
}
}{
"mcpServers": {
"depot-mcp-by-usefulapi": {
"url": "https://depot.usefulapi.io/mcp"
}
}
}name: Depot MCP by usefulapi
version: 0.0.1
schema: v1
mcpServers:
- name: Depot MCP by usefulapi
type: streamable-http
url: https://depot.usefulapi.io/mcp{
"mcpServers": {
"depot-mcp-by-usefulapi": {
"httpUrl": "https://depot.usefulapi.io/mcp"
}
}
}{
"mcpServers": {
"depot-mcp-by-usefulapi": {
"type": "http",
"url": "https://depot.usefulapi.io/mcp"
}
}
}{
"mcpServers": {
"depot-mcp-by-usefulapi": {
"url": "https://depot.usefulapi.io/mcp"
}
}
}goose://extension?url=https%3A%2F%2Fdepot.usefulapi.io%2Fmcp&type=streamable_http&id=depot-mcp-by-usefulapi&name=Depot%20MCP%20by%20usefulapi
It answered our last check on 15 November 2026 in 245 ms. Over 4 checks since 29 September 2026 it answered 4. Status here comes from Neuronto's own probes, not from the publisher.
Yes. It is published by usefulapi.io and served from depot.usefulapi.io, the vendor's own domain: https://depot.usefulapi.io/mcp.
24, as returned by the server's own tools/list on 18 November 2026: depot_cache_delete_entries, depot_cache_list_entries, depot_ci_cancel_run, depot_ci_get_failure_diagnosis, depot_ci_get_job, depot_ci_get_job_logs, depot_ci_get_run_status, depot_ci_list_runs, and 16 more.
It answered our last check on 15 November 2026 in 245 ms. Over 4 checks since 29 September 2026 it answered 4.
Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://depot.usefulapi.io/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.
It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.
Publisher: io.usefulapi. Endpoint host: depot.usefulapi.io. ARD identifier: urn:air:io.usefulapi:mcp:depot.
First indexed 29 September 2026. The tools are exactly what the server returned; nothing on this page
is inferred from its name. Ranking in Neuronto search is never for sale.