io.github.bch1212/modelwatch
NPM · MODELWATCH-MCP · SCANNED SEP 20
Continuous behavioral drift monitoring for LLM apps — catches silent provider model updates.
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 95 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency97
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to bch1212/modelwatch). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 133 days ago).Pass
- Security-disclosure policy not yet verified: we couldn't inspect the source repository.Unverified
Schema Quality & AI Usability77
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 745 tokens (~82/item across 9 items; 9 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management90
- Stability observed for 27 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage92
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 75% 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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 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 io.github.bch1212/modelwatch MCP server?
io.github.bch1212/modelwatch runs locally as an npm package, launched with npx -y modelwatch-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 · modelwatch-mcp
claude mcp add bch1212-modelwatch -- npx -y modelwatch-mcp
{
"mcpServers": {
"bch1212-modelwatch": {
"command": "npx",
"args": [
"-y",
"modelwatch-mcp"
]
}
}
} {
"servers": {
"bch1212-modelwatch": {
"command": "npx",
"args": [
"-y",
"modelwatch-mcp"
]
}
}
} codex mcp add bch1212-modelwatch -- npx -y modelwatch-mcp
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"bch1212-modelwatch": {
"type": "local",
"command": [
"npx",
"-y",
"modelwatch-mcp"
],
"enabled": true
}
}
} openclaw mcp add bch1212-modelwatch --command npx --arg -y --arg modelwatch-mcp
mcp_servers:
bch1212-modelwatch:
command: "npx"
args: ["-y", "modelwatch-mcp"] {
"McpServers": {
"bch1212-modelwatch": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"modelwatch-mcp"
]
}
}
} assistant mcp add bch1212-modelwatch -t stdio -c npx -a -y modelwatch-mcp
{
"mcpServers": {
"bch1212-modelwatch": {
"command": "npx",
"args": [
"-y",
"modelwatch-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
- Security disclosure: fail → unverified ▼ functional
- 18 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.
- 16 Sept 26 −3
- Stability: pass → 0.77 functional
- 15 Sept 26 0
- Stability: 0.97 → pass security
- 14 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.
- 12 Sept 26 +1
- Security disclosure: unverified → fail ▼ functional
- 11 Sept 26 0
- Security disclosure: fail → unverified ▼ functional
- 10 Sept 26 −2
- Stability: pass → 0.83 functional
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/modelwatch-mcp@0.1.1
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 | bch1212/modelwatch |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/bch1212/modelwatch/.github/workflows/publish-mcp.yml@refs/tags/mcp-v0.1.1 |
| Rekor log index | 1486480195 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:3a8e1a7d88b963d5bdb928086dd5f09846d1877be0bb4ea96ed425e4deeb4249274cf2aa2ba91523b9cbf6cbfdf291dca88530b97e1fb89ed430a9fd9 |
Background: How many MCP packages publish verified provenance →
Dependencies 95 packages
| Packages resolved | 95 |
|---|---|
| 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 →
create_endpoint ~130
Register an LLM endpoint to monitor. The workspace must already have a stored API key for the provider (use the dashboard to add one). Returns the new endpoint's id.
| Name | Type | Req | Description |
|---|---|---|---|
| base_url | string | – | Optional. Override base URL for OpenAI-compatible endpoints (vLLM, LiteLLM, Together). |
| model | string | yes | Model identifier, e.g. 'gpt-4o-mini' or 'claude-sonnet-4-6'. |
| name | string | yes | Human-readable label, e.g. 'GPT-4o mini prod'. |
| provider | string | yes | – |
No output schema declared.
No examples provided.
create_spec ~167
Create a behavioral spec. The first run after creation sets the baseline output; subsequent scheduled runs are scored against that baseline across 5 axes (semantic, format, refusal, length, contains). An alert is sent when the drift score crosses the threshold.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | yes | Endpoint to monitor (from list_endpoints). |
| frequency | string | – | How often to run the spec. |
| name | string | yes | Spec label, e.g. 'Refusal canary' or 'JSON schema check'. |
| prompt | string | yes | The exact prompt to send to the model. |
| threshold | string | – | Severity at which to fire an alert. Buckets: low ≥0.05, medium ≥0.15, high ≥0.35, critical ≥0.6. |
No output schema declared.
No examples provided.
get_drift_events ~92
Fetch recent drift events across the workspace, newest first. Each event has spec_id, spec_name, severity, drift_score, axes breakdown, baseline_output, current_output, and detected_at. Use this for weekly review or to drive an automation.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | Max events to return (default 20, max 100). |
| spec_id | string | – | Optional. Filter to one spec. |
No output schema declared.
No examples provided.
get_health ~35
Workspace KPIs: plan, spec count, runs this month, plan limits, active drift events. Useful as a daily status check.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
get_spec_history ~59
Get the run history for a single spec. Returns each run's drift score, severity, axes breakdown, and timestamp — useful for trending charts and reasoning about when behavior shifted.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | integer | – | – |
| spec_id | string | yes | – |
No output schema declared.
No examples provided.
list_endpoints ~37
List the LLM endpoints currently monitored in this workspace. Returns id, name, provider, model, base_url, created_at for each.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
list_specs ~72
List behavioral specs in the workspace. A spec is a stored prompt + expectation that ModelWatch replays on a schedule and diffs against a baseline. Returns id, name, prompt, frequency, threshold, last_severity, and the parent endpoint_id.
| Name | Type | Req | Description |
|---|---|---|---|
| endpoint_id | string | – | Optional. Filter by endpoint. |
No output schema declared.
No examples provided.
reset_baseline ~69
Clear a spec's baseline. The next run will record a new baseline instead of being diffed against the old one. Use this after you've intentionally changed your prompt template, model version, or the behavior you expect — otherwise every future run will look like drift.
| Name | Type | Req | Description |
|---|---|---|---|
| spec_id | string | yes | – |
No output schema declared.
No examples provided.
run_spec ~84
Run a spec on demand and return the drift score immediately. Use this to (1) set the baseline manually right after create_spec, or (2) sanity-check a spec without waiting for the next scheduled run. Returns the drift score, severity bucket, per-axis scores, and the drift_event_id if one was created.
| Name | Type | Req | Description |
|---|---|---|---|
| spec_id | string | yes | From list_specs. |
No output schema declared.
No examples provided.
What is the io.github.bch1212/modelwatch MCP server?
io.github.bch1212/modelwatch is an MCP server listed in the public MCP registry as io.github.bch1212/modelwatch. Continuous behavioral drift monitoring for LLM apps, catches silent provider model updates. This page covers its npm package (modelwatch-mcp).
Is the io.github.bch1212/modelwatch MCP server safe to use?
io.github.bch1212/modelwatch scores 93 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 io.github.bch1212/modelwatch MCP server expose?
io.github.bch1212/modelwatch exposes 9 tools: list_endpoints, create_endpoint, list_specs, create_spec, run_spec, and 4 more. Their descriptions and schemas cost roughly 745 tokens of context every time the server is loaded.
Is the io.github.bch1212/modelwatch MCP server still maintained?
io.github.bch1212/modelwatch 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 io.github.bch1212/modelwatch MCP server under?
io.github.bch1212/modelwatch declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.