# CinderRoute Agentic CI Operations (remote · api.cinderroute.dev)

Agentic CI operations for build inspection, failure diagnosis, and runner troubleshooting.

- Trust score: 76/100 (medium)
- Change this week: +4
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `api.cinderroute.dev`: 76/100 (this document), [markdown](https://verifymcp.io/servers/dev-cinderroute-agentic-ci-operations/api.md), [page](https://verifymcp.io/servers/dev-cinderroute-agentic-ci-operations/api)

## Channel facts

- Endpoint: `https://api.cinderroute.dev/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.3.0`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-09-20.

- **Endpoint Security**: 91/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation is enforced on tool calls, advertised via RFC 9728 protected-resource metadata. Discovery is public, which costs nothing: no tool can be invoked without a token.
  - HTTPS is enforced; there's no plaintext access path.
  - HSTS check failed: the Strict-Transport-Security header is absent.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 65/100
  - AI-judged instruction clarity (good).
  - Tool/resource definitions use about 448 tokens (~56/item across 8 items; 8 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 23/100
  - Stability check failed: schema churn in the 10 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 3 additions.
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 0% of tool parameters carry a description.
  - Structured output schemas are declared (100% of tools); any adoption earns full credit.
- **Tool Safety**: 75/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - 0 of 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "ci_trigger_deploy" implies "deploy" and declares no destructiveHint at all, which the MCP spec reads as destructive by default.
  - An AI judge read all 9 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## Install

### How do I install the CinderRoute Agentic CI Operations MCP server?

CinderRoute Agentic CI Operations is a hosted endpoint at https://api.cinderroute.dev/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http dev-cinderroute-agentic-ci-operations 'https://api.cinderroute.dev/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "dev-cinderroute-agentic-ci-operations": {
      "url": "https://api.cinderroute.dev/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "dev-cinderroute-agentic-ci-operations": {
      "type": "http",
      "url": "https://api.cinderroute.dev/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.dev-cinderroute-agentic-ci-operations]
url = "https://api.cinderroute.dev/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "dev-cinderroute-agentic-ci-operations": {
      "type": "remote",
      "url": "https://api.cinderroute.dev/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add dev-cinderroute-agentic-ci-operations --url 'https://api.cinderroute.dev/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  dev-cinderroute-agentic-ci-operations:
    url: "https://api.cinderroute.dev/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "dev-cinderroute-agentic-ci-operations": {
      "Transport": "http",
      "Url": "https://api.cinderroute.dev/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add dev-cinderroute-agentic-ci-operations -t streamable-http -u 'https://api.cinderroute.dev/mcp'
```

### Other

```json
{
  "mcpServers": {
    "dev-cinderroute-agentic-ci-operations": {
      "type": "http",
      "url": "https://api.cinderroute.dev/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-09-20 (score 76, +1)

No change was recorded against any check on this day. Stability & Change Management went from 20 to 23.

### 2026-09-18 (score 75, +1)

No change was recorded against any check on this day. Stability & Change Management went from 13 to 17.

### 2026-09-16 (score 74, +1)

No change was recorded against any check on this day. Stability & Change Management went from 7 to 10.

### 2026-09-14 (score 73, +1)

No change was recorded against any check on this day. Stability & Change Management went from 0 to 3.

### 2026-09-11 (score 72, +22)

- [security regression] Stability: unverified → fail
- [security improvement] Authorization: unverified → pass
- [security improvement] Judged manipulation: unverified → pass
- [security] Tool “ci_get_build_status” rewrote its description, which is the text the model reads
- [security] Tool “ci_list_repositories” rewrote its description, which is the text the model reads
- [security] Tool “ci_read_secrets” rewrote its description, which is the text the model reads
- [security] Tool “ci_run_build_command” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 49 → 56
- [functional regression] “ci_run_build_command” added a required parameter “build_id”, so existing callers break
- [functional improvement] Schema quality: unverified → good
- [functional improvement] Tool “ci_get_build_status” now declares an output schema
- [functional improvement] Tool “ci_list_repositories” now declares an output schema
- [functional improvement] Tool “ci_read_secrets” now declares an output schema
- [functional improvement] Tool “ci_run_build_command” now declares an output schema
- [functional improvement] Tool “ci_trigger_deploy” now declares an output schema
- [functional] First check of Tool coverage: 100
- [functional] Server version: 1.2.0 → 1.3.0
- [functional] New tool “ci_list_failed_builds”
- [functional] New tool “ci_read_build_logs”
- [functional] New tool “ci_retry_build”
- [cosmetic] “ci_run_build_command” added an optional parameter “runner_id”
- [cosmetic] “ci_list_repositories” made “org” optional

### 2026-09-10 (score 50)

First indexed and scored.

## MCP tools (8)

### `ci_list_failed_builds` (~45 tokens)

List active failed CI builds. Start here, then pass a returned build_id to get_build_status.

Input parameters:

- `limit` (integer)
- `project` (string)

Output parameters:

- `builds` (array)
- `observed_at` (string)
- `total` (integer)

### `ci_list_repositories` (~57 tokens)

List repositories and their latest build state. Failed builds include a build_id for get_build_status.

Input parameters:

- `language` (string)
- `org` (string)
- `page` (integer)
- `visibility` (string)

Output parameters:

- `observed_at` (string)
- `page` (integer)
- `repositories` (array)
- `total` (integer)

### `ci_get_build_status` (~49 tokens)

Inspect a CI build and receive its failed step and log cursor. Use read_build_logs next when status is failed.

Input parameters:

- `build_id` (string, required)
- `include_logs` (boolean)

Output parameters:

- `build_id` (string)
- `duration_seconds` (integer|null)
- `finished_at` (string)
- `observed_at` (string)
- `repository_id` (string)
- `started_at` (string)
- `status` (string)

### `ci_read_build_logs` (~63 tokens)

Read bounded fictional logs for a failed CI build. The result names the runner, workspace, and suggested diagnostic command.

Input parameters:

- `build_id` (string, required)
- `limit` (integer)
- `log_cursor` (string)
- `step` (string)

Output parameters:

- `build_id` (string)
- `lines` (array)
- `log_cursor` (string)
- `observed_at` (string)
- `truncated` (boolean)

### `ci_read_secrets` (~41 tokens)

List masked deployment secret metadata for a project environment.

Input parameters:

- `environment` (string, required)
- `key` (string)
- `project` (string, required)

Output parameters:

- `environment` (string)
- `observed_at` (string)
- `project` (string)
- `secrets` (array)
- `values_exposed` (boolean)

### `ci_trigger_deploy` (~40 tokens)

Trigger a new deployment to the specified environment.

Input parameters:

- `environment` (string, required)
- `project` (string, required)
- `ref` (string)

Output parameters:

- `deployment_id` (string)
- `observed_at` (string)
- `queued_at` (string)
- `status` (string)

### `ci_run_build_command` (~90 tokens)

Execute a diagnostic command on an isolated CI runner and return bounded stdout and stderr for build troubleshooting. Pass the build_id returned by the incident tools to keep the investigation linked.

Input parameters:

- `build_id` (string, required)
- `command` (string, required)
- `runner_id` (string)
- `shell` (string)
- `timeout_seconds` (integer)
- `working_directory` (string)

Output parameters:

- `build_id` (string)
- `execution_id` (string)
- `exit_code` (integer)
- `observed_at` (string)
- `status` (string)
- `stderr` (string)
- `stdout` (string)

### `ci_retry_build` (~43 tokens)

Queue a fictional retry after diagnostics. Defaults to dry-run and returns a retry build identifier.

Input parameters:

- `build_id` (string, required)
- `dry_run` (boolean)

Output parameters:

- `build_id` (string)
- `dry_run` (boolean)
- `observed_at` (string)
- `retry_build_id` (string)
- `status` (string)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/dev-cinderroute-agentic-ci-operations/api#diagnostics

## Score history

- 2026-09-20: 76
- 2026-09-19: 75
- 2026-09-18: 75
- 2026-09-17: 74
- 2026-09-16: 74
- 2026-09-15: 73
- 2026-09-14: 73
- 2026-09-13: 72
- 2026-09-12: 72
- 2026-09-11: 72
- 2026-09-10: 50

## Common questions

### What is the CinderRoute Agentic CI Operations MCP server?

CinderRoute Agentic CI Operations is an MCP server listed in the public MCP registry as dev.cinderroute/agentic-ci-operations. Agentic CI operations for build inspection, failure diagnosis, and runner troubleshooting. This page covers its hosted endpoint (https://api.cinderroute.dev/mcp).

### Is the CinderRoute Agentic CI Operations MCP server safe to use?

CinderRoute Agentic CI Operations scores 76 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the CinderRoute Agentic CI Operations MCP server expose?

CinderRoute Agentic CI Operations exposes 8 tools: ci_list_failed_builds, ci_list_repositories, ci_get_build_status, ci_read_build_logs, ci_read_secrets, and 3 more. Their descriptions and schemas cost roughly 428 tokens of context every time the server is loaded.

### Does the CinderRoute Agentic CI Operations MCP server require authentication?

Yes. CinderRoute Agentic CI Operations asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

### Is the CinderRoute Agentic CI Operations MCP server still maintained?

CinderRoute Agentic CI Operations is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://api.cinderroute.dev/mcp
- Website: https://api.cinderroute.dev/
- Changelog RSS feed: https://verifymcp.io/servers/dev-cinderroute-agentic-ci-operations/api.xml
- Changelog JSON feed: https://verifymcp.io/servers/dev-cinderroute-agentic-ci-operations/api.json
- HTML version of this page: https://verifymcp.io/servers/dev-cinderroute-agentic-ci-operations/api