autorouter
NPM · AUTOROUTER-MCP · SCANNED SEP 20
An MCP capability router: one search tool instead of every server's tool schema.
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
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to Webb-Ventures/autorouter). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 3 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability83
- 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 556 tokens (~139/item across 4 items; 4 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 Management77
- Stability observed for 23 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 50% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 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 autorouter MCP server?
autorouter runs locally as an npm package, launched with npx -y autorouter-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 · autorouter-mcp
claude mcp add webb-ventures-autorouter -- npx -y autorouter-mcp
{
"mcpServers": {
"webb-ventures-autorouter": {
"command": "npx",
"args": [
"-y",
"autorouter-mcp"
]
}
}
} {
"servers": {
"webb-ventures-autorouter": {
"command": "npx",
"args": [
"-y",
"autorouter-mcp"
]
}
}
} codex mcp add webb-ventures-autorouter -- npx -y autorouter-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"webb-ventures-autorouter": {
"type": "local",
"command": [
"npx",
"-y",
"autorouter-mcp"
],
"enabled": true
}
}
} openclaw mcp add webb-ventures-autorouter --command npx --arg -y --arg autorouter-mcp
mcp_servers:
webb-ventures-autorouter:
command: "npx"
args: ["-y", "autorouter-mcp"] {
"McpServers": {
"webb-ventures-autorouter": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"autorouter-mcp"
]
}
}
} assistant mcp add webb-ventures-autorouter -t stdio -c npx -a -y autorouter-mcp
{
"mcpServers": {
"webb-ventures-autorouter": {
"command": "npx",
"args": [
"-y",
"autorouter-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 73 to 77. That category is still filling its 30-day observation window: 22 days of observed history at the previous scan, 23 at this one. The score rises as the window fills, whether or not the server changes.
- 18 Sept 26 +42
- Injection markers: unverified → pass ▲ security
- Tool coverage: unverified → 100 ▲ functional
- Schema quality: unverified → 100 ▲ functional
- MCP protocol: unverified → pass ▲ functional
- Stability: unverified → 0.70 ▲ functional
- Package version: 0.2.3 → 0.2.7 functional
- 17 Sept 26 0
- Package version: 0.2.3 → 0.2.7 functional
- 16 Sept 26 −40
- Malware scan: pass → unverified ▼ security
- Tool safety: pass → unverified ▼ security
- Stability: 0.60 → unverified ▼ security
- Capabilities: pass → unverified ▼ functional
- Tool coverage: 100 → unverified ▼ functional
- Schema quality: 100 → unverified ▼ functional
- Package version: 0.2.3 → 0.2.6 functional
- Package version: 0.2.3 → 0.2.5 functional
- Package version: 0.2.3 → 0.2.4 functional
- 14 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 53 to 57. That category is still filling its 30-day observation window: 16 days of observed history at the previous scan, 17 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 9 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 7 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
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/autorouter-mcp@0.2.7
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | Webb-Ventures/autorouter |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/Webb-Ventures/autorouter/.github/workflows/publish.yml@refs/heads/release/v0.2.7 |
| Rekor log index | 2868420867 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:210644cda9222672dce03b36bba5a5aaf2cab6da0c238f2614147567bf283459297b65fff832ccffab7bc8a106b1c21cf4ca27028ee59695761b61dc6 |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| 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 →
add_server ~112
Register a new MCP server behind the router, instead of running `claude mcp add`. Pass url or command+args, or json for a pasted {"mcpServers":{…}} snippet. Rejected without confirm: true.
| Name | Type | Req | Description |
|---|---|---|---|
| args | array | – | – |
| command | string | – | – |
| confirm | boolean | – | – |
| env | object | – | – |
| headers | object | – | – |
| json | string | – | – |
| name | string | yes | – |
| url | string | – | – |
No output schema declared.
No examples provided.
call_capability ~85
Run a capability by id and return its result. Works for tools, prompts and resources; skills and commands are executed by following the text from describe_capability instead.
| Name | Type | Req | Description |
|---|---|---|---|
| arguments | object | – | Arguments matching the capability's input schema. |
| confirm | boolean | – | Set true to proceed with a capability that requires explicit confirmation. |
| id | string | yes | Capability id to invoke. |
No output schema declared.
No examples provided.
describe_capability ~61
Get full detail for one capability id from find_capabilities: the complete input schema for a tool, or the full instruction text for a skill or command.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | Capability id, e.g. mcp:supabase/execute_sql |
No output schema declared.
No examples provided.
find_capabilities ~140
Search every available tool, skill, prompt and command by what you are trying to do, and get back only the ones that fit. Catalog: 0 providers · . Use this whenever a task might need a capability you cannot already see — searching is cheap and the catalog is much larger than your tool list.
| Name | Type | Req | Description |
|---|---|---|---|
| kind | string | – | Optional: restrict results to one kind of capability. |
| limit | number | – | Max results (default 8). |
| query | string | yes | What you are trying to accomplish, in plain language. Describe the goal, not a guessed tool name. |
| server | string | – | Optional: restrict to one provider. |
No output schema declared.
No examples provided.
What is the autorouter MCP server?
autorouter is an MCP server listed in the public MCP registry as io.github.Webb-Ventures/autorouter. An MCP capability router: one search tool instead of every server's tool schema. This page covers its npm package (autorouter-mcp).
Is the autorouter MCP server safe to use?
autorouter scores 92 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. Its build provenance is signed and verified. 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 autorouter MCP server expose?
autorouter exposes 4 tools: find_capabilities, describe_capability, call_capability, add_server. Their descriptions and schemas cost roughly 398 tokens of context every time the server is loaded.
Is the autorouter MCP server still maintained?
autorouter 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.
What licence is the autorouter MCP server under?
autorouter declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.