Pack local or remote codebases into AI-friendly files that LLMs and coding agents can read or search
Tools
diffci_validation_plan
Plan change-aware CI validation, affected-test selection, test impact analysis, or GitHub Actions workflow checks. Returns a safe local DiffCI command without accessing the checkout or executing it.
action string
Validation action. Defaults to check.
repo string
Optional local repository path to pass as a single --repo argument.
platform string
Shell used only to render the display command. Defaults to posix.
A call is made on an account: it counts against an allowance and the publisher sees it, which is why this one asks who you are first.
94/100
trust score
103
downloads a day
remote
via our gateway
7k
downloads in 30d
What it does
Observation-only CI/CD validation for AI coding agents.
Quickstart
# 1 — sign in once: npx mcprush@latest login
# it asks for a key from mcprush.com/dashboard#access
# 2 — install
npx mcprush@latest add diffci/diffci-mcp
# 3 — ask your agent for something these tools do
# diffci_validation_plan, diffci_interpret_report, diffci_verify_workflow_text
Windows PowerShell says 'running scripts is disabled on this system'? Run Set-ExecutionPolicy -Scope CurrentUser RemoteSigned once, or type npx.cmd instead of npx (codex.cmd, gemini.cmd, grok.cmd likewise). PowerShell 7 needs neither.
DiffCI costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
PublisherVerified · since 2026
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. Nothing here runs on your machine — this server runs on the publisher’s own infrastructure behind our gateway, and what you install is the connection to it.
Claude Codedeclared by this listing
Claude Code has its own MCP command, and the key rides on it as a header — the gateway refuses a call that carries none. Claude Code reads MCPRUSH_KEY each time it connects, so the key stays out of its config: export your key from Access in your shell profile (macOS, Linux), or run setx MCPRUSH_KEY <your key> and open a new terminal (Windows). Or let npx mcprush@latest add diffci/diffci-mcp write the entry with the key for you; --scope user makes it available in every project.
claude mcp add --transport http --scope user diffci-mcp https://mcprush.com/gw/diffci-mcp/mcp --header 'Authorization: Bearer ${MCPRUSH_KEY}'Reconnect, or start a new session, and the tools appear in the model’s tool list.
Free to install on mcprush: no card. The gateway still answers a key, so you sign in once — which is also what gives you saved lists, release alerts and a budget cap.
What it writes
One config entry pointing at the gateway. The server itself runs on the publisher’s own infrastructure, so nothing from this listing executes on your machine.
What you approve
3 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.
Plan change-aware CI validation, affected-test selection, test impact analysis, or GitHub Actions workflow checks. Returns a safe local DiffCI command without accessing the checkout or executing it.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| action | string | no | Validation action. Defaults to check. |
| repo | string | no | Optional local repository path to pass as a single --repo argument. |
| platform | string | no | Shell used only to render the display command. Defaults to posix. |
Validate and summarize a DiffCI observation report, including selective or full mode, affected-test counts, fallbacks, non-interference evidence, and the conservative next action.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| report | object | yes | A diffci.observation.v1 JSON report. |
Perform a stateless preliminary safety check of GitHub Actions YAML: dedicated observer job, continue-on-error, dependency isolation, read-only permissions, and immutable DiffCI references.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| workflow | string | yes | One GitHub Actions workflow YAML document. |
Free
$0 forever
- Every tool, no call limit, and mcprush charges nothing
- A buyer key from your dashboard — the gateway refuses a call without one
- Answers through our gateway, so every call is in your log
- 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 DiffCI or to call it, and its free tier carries no monthly call limit.
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 0.3.9 · scanned 14 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 score94
Findings7 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digestdb1c1074cd65e4b19b7cb6b8d58a4e76cea6cb4cd692932b0ff72db4232760d4
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 (5 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 |
|---|---|---|
| diffci_verify | no tags | |
| diffci_verify_changed | no tags | |
| diffci_check | no tags | |
| diffci_init | no tags | |
| diffci_verify_workflow | 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 digestdb1c1074cd65e4b1
Scanned2026-10-14
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
The gateway serves every install the publisher’s current release, so a release cannot be pinned or rolled back to here yet. The history below is for reading; the current release on file is 0.3.9.
0.3.9
7 Oct 2026
latestNo release note was published with this version.
0.3.6
5 Oct 2026
No release note was published with this version.
0.3.3
4 Oct 2026
No release note was published with this version.
0.3.2
3 Oct 2026
No release note was published with this version.
0.3.1
2 Oct 2026
No release note was published with this version.
0.2.11
25 Sep 2026
No release note was published with this version.
0.2.9
25 Sep 2026
No release note was published with this version.
0.2.4
22 Sep 2026
No release note was published with this version.
0.2.3
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 DiffCI 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.