The official Svelte MCP server providing docs and autofixing tools for Svelte development
Nothing to run from here
Tracegate CI 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.
94/100
trust score
183
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
Local CI broker and test-impact ledger for coding agents: queue, lane modes and red-run packets.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user tracegate-ci-mcp '--' npx -y tracegate-ci mcp
# 2 — ask your agent for something these tools do
# queue_status, explain_job, history and 14 more
Tracegate CI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
DAAll 1 server
davidscotttufts1 server
1 category
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 Tracegate CI 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 tracegate-ci-mcp '--' npx -y tracegate-ci 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
17 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.
The machine's CI capacity right now: tokens in use, running leases (class, label, tokens, fence), the queue in order, and the reserved start time of the first blocked job.
No parameter schema on file.
Why a lease is where it is: its queue position, the jobs ahead of it, what holds the capacity, and when it is reserved to start.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | A job id such as "j42" (printed by tracegate lease). |
The most recent broker events (enqueue, grant, preempt, release, expire, advice), newest last. Each carries a sequence number and timestamp.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| n | integer | no | — |
This machine's hardware (cores, performance cores, RAM, container limits), its latest load / available memory / memory pressure / swap / thermal reading, and the cpu and memory budgets the broker is handing out right now, with the reasons. Each running lease's measured memory is included. Read it…
No parameter schema on file.
Recent red runs on this machine (newest first; ones an opinion escalated first), each with its packet id, lane, head, how many files failed, how many were Tracegate MISSES, and the latest opinion if any. Read a packet with read_red.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| n | integer | no | — |
One red-run packet: every failing file with its failure text, what Tracegate predicted for it and why, whether it was a MISS and how its re-run alone went, its past misses and triage, the files changed against the base, a clipped diff, and the machine load. Use it to form an opinion; read the code…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Recent lockfile runs (newest first): one dependency packet each, with how many packages changed and how many files failed, and whether a prediction was recorded. Read one with read_deps.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| n | integer | no | — |
One dependency packet: every package the lockfile change moved (name, from → to, semver class, native code, whether the vitest process loaded it), the lane size, and which files failed in the full run. Read the changelogs and the code that uses the package before predicting.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
Tracegate's test-selection mode per lane (off, shadow or enforce) and why, from the repository's tracegate.config.json.
No parameter schema on file.
Per lane, what reusing verdicts would have saved so far: file runs and test time that could have been skipped, the projection at the audit rate, misses, and how far the lane is from its entry bar. Read from the shadow log, so it has numbers before enforcement starts.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lane | string | no | — |
Tracegate's own error rates per lane: misses per checked verdict and per run with 95% Wilson intervals, the triage of each miss, the longest a hole could have gone undetected, audit cost, and the Red Reader and Conductor scores. Read from the append-only logs.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| lane | string | no | — |
The local merge train: the PRs queued for each target branch (id, ref, pinned commit) and the latest landed, rejected and dropped events with their reasons.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| target | string | no | — |
Record an ESCALATE-ONLY opinion on a red-run packet. It is stored and shown to people; it never lowers a verdict, never marks anything a flake, never merges or re-runs anything. Its one effect: verdict real + escalate true + confidence ≥ 0.7 on a file that was a MISS raises the automatic flake to…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| verdict | string | yes | — |
| escalate | boolean | yes | — |
| confidence | number | yes | — |
| reasons | string | yes | — |
| files | array | no | — |
| owner | string | no | — |
Record a SHADOW prediction for a dependency packet: which test files the package change can affect (a list of files, or "all", or "none"). It is scored against the full run the gate already did; nothing reads it back and it never skips a test.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
| affected | yes | — | |
| confidence | number | yes | — |
| reasons | string | yes | — |
Queue a branch or ref for the local merge train, pinned to its current commit. It only queues: a person or a gate runs tracegate train run, which lands it only if its exact merge commit is gated green.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| pr | string | yes | An id, or <id>=<ref>. A bare id is also the ref. |
| target | string | no | — |
Cancel a job that is still QUEUED (never a running one). The job's own wrapper then exits.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | — |
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under Apache-2.0
- 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 Tracegate CI 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 94 / 100
Release 0.10.2 · scanned 5 Nov 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 score94
Findings10 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestff6390e8d7c3ab5241efab4ea37b9094acc9f340f0ba2916e8b7a3e19313e2c4
Score vectorthreat 100 → client 94
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| 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 (17 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 |
|---|---|---|
| queue_status | no tags | |
| explain_job | no tags | |
| history | no tags | |
| machine_load | no tags | |
| red_runs | no tags | |
| read_red | no tags | |
| deps_runs | no tags | |
| read_deps | no tags | |
| lane_mode | no tags | |
| savings | no tags | |
| report_card | no tags | |
| train_status | no tags | |
| bus_status | no tags | |
| annotate_red | state-write | state-write: declares readOnlyHint: false |
| annotate_deps | state-write | state-write: declares readOnlyHint: false |
| train_add | state-write | state-write: declares readOnlyHint: false |
| cancel_queued | state-write | state-write: declares readOnlyHint: false, destructiveHint: true |
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 digestff6390e8d7c3ab52
Scanned2026-11-05
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 0.10.2. Pin a release below and the command asks for exactly that one.
0.10.2
4 Nov 2026
latestNo release note was published with this version.
0.10.1
2 Nov 2026
No release note was published with this version.
0.9.1
undated
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
—
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 Tracegate CI 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.