comber
NPM · COMBER-MCP · SCANNED SEP 20
Every-click AI QA: walks your whole app from a preview URL and reports broken clicks and errors.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 35 of 111 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency32
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Provenance check failed: no build-provenance attestation is published. See how to fix → View diagnostics → Fail
- License check failed: the license (SEE LICENSE IN LICENSE) isn't a recognized OSI-approved license. See how to fix → Fail
- Actively maintained (last published 35 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability79
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 464 tokens (~154/item across 3 items; 3 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management97
- Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 3 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 3 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the comber MCP server?
comber runs locally as an npm package, launched with npx -y comber-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · comber-mcp
claude mcp add io-codecomber-comber -- npx -y comber-mcp
{
"mcpServers": {
"io-codecomber-comber": {
"command": "npx",
"args": [
"-y",
"comber-mcp"
]
}
}
} {
"servers": {
"io-codecomber-comber": {
"command": "npx",
"args": [
"-y",
"comber-mcp"
]
}
}
} codex mcp add io-codecomber-comber -- npx -y comber-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"io-codecomber-comber": {
"type": "local",
"command": [
"npx",
"-y",
"comber-mcp"
],
"enabled": true
}
}
} openclaw mcp add io-codecomber-comber --command npx --arg -y --arg comber-mcp
mcp_servers:
io-codecomber-comber:
command: "npx"
args: ["-y", "comber-mcp"] {
"McpServers": {
"io-codecomber-comber": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"comber-mcp"
]
}
}
} assistant mcp add io-codecomber-comber -t stdio -c npx -a -y comber-mcp
{
"mcpServers": {
"io-codecomber-comber": {
"command": "npx",
"args": [
"-y",
"comber-mcp"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 20 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 −3
- Stability: pass → 0.80 functional
- 14 Sept 26 0
- Stability: 0.97 → pass security
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 −1
- Stability: pass → 0.90 functional
- 10 Sept 26 0
- Stability: 0.97 → pass security
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed npm/comber-mcp@0.1.4
Provenance No attestation
The registry publishes no build provenance for this version, so there is nothing to verify.
| Result | No attestation |
|---|---|
| Ecosystem | npm |
Background: How many MCP packages publish verified provenance →
Dependencies 111 packages
| Packages resolved | 111 |
|---|---|
| Stale | 35 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
comber_api_check comber check (API) ~164
Exercise an API surface with Comber: an OpenAPI spec, a GraphQL endpoint, or a recorded HAR. Reports contract drift, error responses, and broken operations. Read-only by default.
| Name | Type | Req | Description |
|---|---|---|---|
| allowPrivateTarget | boolean | – | Target a private/staging base you own (bypasses the SSRF egress guard). |
| apiBase | string | – | Base URL for the API (required with --openapi). |
| graphql | string | – | GraphQL endpoint URL to introspect + exercise. |
| har | string | – | Path to a recorded HAR to replay and check for drift. |
| openapi | string | – | Path or URL to an OpenAPI document. |
| strict | boolean | – | Return a failing summary if any 'fail' finding is present. |
No output schema declared.
No examples provided.
comber_check comber check (web) ~239
Crawl a web app / site / SaaS surface with Comber and report broken clicks, dead ends, console errors, and broken links. Read-only by default (does not submit forms or trigger mutations). Great to run against a preview/staging URL before merging. Optional LLM finding-judge only runs if ANTHROPIC_API_KEY is set in the environment.
| Name | Type | Req | Description |
|---|---|---|---|
| allowWrites | boolean | – | DANGER: exercise mutating controls/methods (submits, deletes). Off by default. Only enable against a disposable target you own. |
| crossOrigin | boolean | – | Follow links off the start origin. Default: same-origin only. |
| externalLinks | boolean | – | Verify external links (HEAD/GET). Default: off. |
| maxActions | integer | – | Cap on total actions taken (runaway-cost backstop). |
| maxStates | integer | – | Cap on distinct app states to explore (runaway-cost backstop). |
| strict | boolean | – | Return a failing summary if any 'fail' finding is present (gate a merge). |
| url | string | yes | The URL to crawl (e.g. a preview deployment). |
No output schema declared.
No examples provided.
comber_report comber report (full findings) ~61
Read the full findings list from a previous comber run. Pass the runDir returned by comber_check / comber_api_check.
| Name | Type | Req | Description |
|---|---|---|---|
| runDir | string | yes | The runDir path returned by a prior comber_check / comber_api_check call. |
No output schema declared.
No examples provided.
What is the comber MCP server?
comber is an MCP server listed in the public MCP registry as io.codecomber/comber. Every-click AI QA: walks your whole app from a preview URL and reports broken clicks and errors. This page covers its npm package (comber-mcp).
Is the comber MCP server safe to use?
comber scores 82 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. 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 comber MCP server expose?
comber exposes 3 tools: comber_check, comber_api_check, comber_report. Their descriptions and schemas cost roughly 464 tokens of context every time the server is loaded.
Is the comber MCP server still maintained?
comber 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.