mcp.bencher.dev
https://mcp.bencher.dev/mcp
active Production-safe Score 93/100 http no auth
At a glance
| Endpoint | https://mcp.bencher.dev/mcp |
|---|---|
| Source | https://raw.githubusercontent.com/bencherdev/bencher/main/plugins/bencher/mcp.json |
| Transport | http |
| Tools | 37 |
| Auth | none |
| First seen | 2026-11-01 19:08:21 |
| Last checked | 2026-11-17 21:55:31 |
Observed reliability
| 7-day uptime | 100% |
|---|---|
| 24-hour uptime | 100% |
| Handshake success | 100% |
| Latency p50 / p95 | 509 / 760 ms |
| Last successful check | 2026-11-17 21:55:31 |
Measured by Arclan's validator via repeated live MCP handshakes. How this is computed →
Tools (37)
submit_run— Submit benchmark results to create a run. The `results` field takes the raw output of a benchmark harness as strings; the server parses themlist_projects— List an organization's projects. The `organization` argument accepts an organization slug or UUID. With a project API key (`bencher_run_`),view_project— View a project. The `project` argument accepts a project slug or UUID.list_reports— List reports for a project, sorted by date time in reverse chronological order by default. Results and alerts are collapsed to counts unlesscreate_report— Create a report from raw benchmark results for an existing branch and testbed. Prefer `submit_run` unless the branch and testbed are alreadyview_report— View a report, including its full results and any alerts.list_branches— List branches for a project.create_branch— Create a branch for a project.view_branch— View a branch. The `branch` argument accepts a branch slug or UUID.update_branch— Update a branch. Project API keys (`bencher_run_`) cannot rename branches.list_testbeds— List testbeds for a project.create_testbed— Create a testbed for a project.view_testbed— View a testbed. The `testbed` argument accepts a testbed slug or UUID.update_testbed— Update a testbed. Project API keys (`bencher_run_`) cannot rename testbeds.list_benchmarks— List benchmarks for a project.create_benchmark— Create a benchmark for a project.view_benchmark— View a benchmark. The `benchmark` argument accepts a benchmark slug or UUID.update_benchmark— Update a benchmark. Project API keys (`bencher_run_`) cannot rename benchmarks.list_measures— List measures for a project (e.g. latency, throughput).create_measure— Create a measure for a project.view_measure— View a measure. The `measure` argument accepts a measure slug or UUID.update_measure— Update a measure. Project API keys (`bencher_run_`) cannot rename measures.list_thresholds— List thresholds for a project. A threshold is a branch, testbed, and measure with a statistical model, checking a filter over the benchmark'create_threshold— Create a threshold for a project: a branch, testbed, and measure with a statistical model used to detect performance regressions. `parameterview_threshold— View a threshold. The `threshold` argument is a threshold UUID.update_threshold— Update a threshold's statistical model, or remove the model by setting it to null.list_alerts— List performance alerts for a project, generated when a threshold boundary is exceeded.view_alert— View an alert, including the boundary that was exceeded. The `alert` argument is an alert UUID.update_alert— Update an alert. Project API keys (`bencher_run_`) can only update the alert status (e.g. acknowledge or dismiss).view_metric— View a single metric with its full context: report, branch, testbed, benchmark, measure, and any threshold boundary. The `metric` argument iquery_perf— Query benchmark metrics over time for a project, as the plot that Bencher draws. This is the primary tool for investigating performance histlist_plots— List saved dashboard plots for a project.create_plot— Create a saved dashboard plot for a project. A project can have a maximum of 64 plots at a time.view_plot— View a saved dashboard plot. The `plot` argument is a plot UUID.update_plot— Update a saved dashboard plot. The `plot` argument is a plot UUID.list_jobs— List bare metal runner jobs for a project.view_job— View a bare metal runner job. The `job` argument is a job UUID.
Validation history
| Checked | Reachable | Handshake | Latency | Score | State |
|---|---|---|---|---|---|
| 2026-11-17 21:55:31 | ✓ | ✓ | 589 ms | 90 | active |
| 2026-11-17 21:40:17 | ✓ | ✓ | 536 ms | 90 | active |
| 2026-11-17 21:25:00 | ✓ | ✓ | 527 ms | 90 | active |
| 2026-11-17 21:09:51 | ✓ | ✓ | 446 ms | 90 | active |
| 2026-11-17 20:54:47 | ✓ | ✓ | 375 ms | 90 | active |
| 2026-11-17 20:39:43 | ✓ | ✓ | 430 ms | 90 | active |
| 2026-11-17 20:24:42 | ✓ | ✓ | 373 ms | 90 | active |
| 2026-11-17 20:09:28 | ✓ | ✓ | 537 ms | 90 | active |
| 2026-11-17 19:53:39 | ✓ | ✓ | 427 ms | 90 | active |
| 2026-11-17 19:38:37 | ✓ | ✓ | 474 ms | 90 | active |
| 2026-11-17 19:23:19 | ✓ | ✓ | 772 ms | 90 | active |
| 2026-11-17 19:08:10 | ✓ | ✓ | 347 ms | 90 | active |
| 2026-11-17 18:52:51 | ✓ | ✓ | 581 ms | 90 | active |
| 2026-11-17 18:37:48 | ✓ | ✓ | 450 ms | 90 | active |
| 2026-11-17 18:22:46 | ✓ | ✓ | 395 ms | 90 | active |
Query this programmatically
Agents can pull this record live over the MCP protocol or REST:
get_server("https://mcp.bencher.dev/mcp") # via the Arclan MCP endpoint https://arclan.ai/mcp
GET https://arclan.ai/api/registry/mcp-bencher-dev-mcp # JSON