Thin MCP server for GrowthBook — skill loader + authenticated API passthrough
Nothing to run from here
Tracewatch is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
7
tools declared
local
runs on your machine
—
downloads a day
What it does
Observability, tracking, and root-cause for Security Wave scans and findings.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user tracewatch-mcp '--' npx -y @reneturcios/tracewatch mcp
# 2 — ask your agent for something these tools do
# ingest_scan, diff_scans, finding_provenance and 4 more
Tracewatch costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
CLAll 34 servers
CloudCorpRecords34 servers
13 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Tracewatch as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user tracewatch-mcp '--' npx -y @reneturcios/tracewatch mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
7 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
Run hookcheck, actionpin, injectcheck, mcpvet, depguard, and flowcheck against a local repo path and store the results as a timestamped scan record with stable finding IDs. Returns the scan record and every finding observation. Use this to start or refresh tracking for a repo.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | yes | Local path of the repo or directory to scan |
| name | string | no | Repo key to file the scan under (default: GitHub slug from the git remote, else the directory name) |
| tools | array | no | Subset of tools to run (default: all six) |
Diff two scans of a repo (default: the last two). Reports NEW, RESOLVED, and CHANGED findings, verdict moves, and action ref events with both refs spelled out, including pin regressions (PINNED to MUTABLE or BRANCH) and bare ref moves on pinned actions.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | yes | Repo key used at ingest |
| from | string | no | Earlier scanId (default: the scan before to) |
| to | string | no | Later scanId (default: the latest scan) |
Root-cause provenance for one finding: the introducing commit from git pickaxe on the finding's content, the current-line commit from git blame, the associated GitHub PR when the API answers, and the finding's ref history from the scan store. Confirmed evidence, inferences, and unestablished items…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | yes | Repo key used at ingest |
| findingId | string | yes | Full findingId (tw_...) or a prefix of at least 8 characters |
| path | string | no | Local clone path to run git evidence against (default: the path recorded at ingest) |
Health report for a repo across all its scans: verdict trend, open findings by tool and severity, resolved count, mean time open for resolved findings, all action ref events, and watch detection latency stats (count, median, max time-to-detect).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | yes | Repo key used at ingest |
Summarize the tracewatch store: every tracked repo with its scan count, last scan time, open finding count, detection count, and median time-to-detect. Use this to see what is being watched and tracked before drilling into one repo.
No parameter schema on file.
List tracked findings for a repo with derived status. Filter by tool, severity, and status (open, resolved, or all; default open). Each entry carries the stable findingId usable with finding_provenance and explain_finding.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | yes | Repo key used at ingest |
| tool | string | no | — |
| severity | string | no | — |
| status | string | no | — |
The full evidence bundle for one finding, written to act on: the tracked finding (status, first and last seen, content versions), its scan history is summarized in the provenance record, and the provenance itself (introducing commit, PR, ref history, confirmed versus inferred versus not…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| repo | string | yes | Repo key used at ingest |
| findingId | string | yes | Full findingId (tw_...) or a prefix of at least 8 characters |
| path | string | no | Local clone path for git evidence (default: the path recorded at ingest) |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Tracewatch or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.2.2 · scanned 28 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings2 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest45a391bc3be6bfdb25ea7e3b3c1f5f274dca49d5fec0e4a25734bc2e4428e4e9
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (7 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| ingest_scan | no tags | |
| diff_scans | no tags | |
| finding_provenance | no tags | |
| repo_health | no tags | |
| watch_status | no tags | |
| list_findings | no tags | |
| explain_finding | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest45a391bc3be6bfdb
Scanned2026-10-28
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.2.2. Pin a release below and the command asks for exactly that one.
0.2.2
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Tracewatch can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.