Server providing Argo CD integration for MCP clients.
Nothing to run from here
Runner 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
96
downloads in 30d
local
runs on your machine
44
tools declared
What it does
Self-hosted MCP for controlled AI development and staging without a general-purpose remote shell.
Quickstart
This package runs as a local HTTP server (Streamable HTTP), not over stdio, so a client cannot start it as a process. Start it in a terminal with uvx aifordable-runner-mcp and keep it running, then add the address it listens on to your client as a remote server; that address is not recorded here, so there is no entry to copy.
Publishernot claimed
BLAll 1 server
Blacksp1d3r1 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 Runner 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.
This package runs as a local HTTP server (Streamable HTTP), not over stdio, so a client cannot start it as a process. Start it in a terminal with uvx aifordable-runner-mcp and keep it running, then add the address it listens on to your client as a remote server; that address is not recorded here, so there is no entry to copy.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Return safe Runner MCP runtime state without private host metadata.
No parameter schema on file.
Return bounded safe runtime checks without paths, endpoints or secrets.
No parameter schema on file.
Start a canonical main-only Runner MCP self-update job.
No parameter schema on file.
Return safe persisted status for one Runner MCP self-update job.
No parameter schema on file.
List only the projects explicitly configured for Runner MCP.
No parameter schema on file.
List built-in, allow-listed project adapters.
No parameter schema on file.
Inspect safe adapter capabilities without exposing the project path.
No parameter schema on file.
Return operator-stop and rollback-retention safety status without private paths.
No parameter schema on file.
Return a safe registration-level status for one allow-listed project.
No parameter schema on file.
Read a bounded page from an allowed UTF-8 project text file.
No parameter schema on file.
List one allowed project directory without recursive traversal.
No parameter schema on file.
Return safe metadata for an allowed project file or directory.
No parameter schema on file.
Synchronize one staging project to an exact commit from its configured origin.
No parameter schema on file.
List configured and fixed safe adapter test profiles without private argv.
No parameter schema on file.
Start one predefined test profile and return a job identifier.
No parameter schema on file.
Return safe metadata for a test job.
No parameter schema on file.
Return safe queue capacity and per-project scheduling state.
No parameter schema on file.
Return bounded worker-pool capacity without process details.
No parameter schema on file.
Return safe status for one queued or active test job.
No parameter schema on file.
Cancel one queued or active test job by opaque job identifier.
No parameter schema on file.
Return a bounded page from a scrubbed test-job log.
No parameter schema on file.
Request cancellation of one running test job.
No parameter schema on file.
List configured service aliases and allowed actions without private unit names.
No parameter schema on file.
Return safe status and health information for one service alias.
No parameter schema on file.
Start one explicitly allow-listed service alias.
No parameter schema on file.
Stop one explicitly allow-listed service alias.
No parameter schema on file.
Restart one explicitly allow-listed service alias.
No parameter schema on file.
List safe database-backup metadata without paths or credentials.
No parameter schema on file.
Create a private PostgreSQL backup for one configured project.
No parameter schema on file.
Create a short-lived human approval plan for migration, deploy or rollback.
No parameter schema on file.
Return safe status for a short-lived human approval plan.
No parameter schema on file.
Run the configured read-only migration status command.
No parameter schema on file.
Apply migrations only after consuming a matching human approval.
No parameter schema on file.
Return a safe read-only staging deployment plan.
No parameter schema on file.
Start a staging deploy only after consuming a matching human approval.
No parameter schema on file.
Return safe persisted status for one deployment job.
No parameter schema on file.
List safe staging release metadata and retention/rollback state.
No parameter schema on file.
Return the one-step rollback target and database-boundary safety state.
No parameter schema on file.
Start one rollback only after consuming a matching human approval.
No parameter schema on file.
Return safe status for an asynchronous rollback job.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
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 Runner 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 0.1.3 · scanned 15 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
Findings10 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationsource
Surface digest58185c2324822be4583fe3345a53c4bc54902b2d58de80ca8d4da7890cb3f21a
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 (44 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>".
37 of the 44 recovered tools are registered only when fabric_bridge is not None is false (src/runner_mcp/server.py:753) — typically when a key or option is configured. They are part of the server's surface and were analysed; a server started without that configuration exposes only the other 7.
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.
7 tools are registered unconditionally · 37 more only when fabric_bridge is not None is false (src/runner_mcp/server.py:753) — typically when a key or option is configured. All 44 are in the table below and were analysed; the conditional ones are marked.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| runtime_status | no tags | |
| runtime_doctor | no tags | |
| fabric_bootstrap | no tags | |
| fabric_bootstrap_status | no tags | |
| self_update | no tags | |
| self_update_status | no tags | |
| list_projects | no tags | |
| list_project_adapters conditional | no tags | |
| project_capabilities conditional | no tags | |
| safety_status conditional | no tags | |
| project_status conditional | no tags | |
| read_project_file conditional | no tags | |
| list_project_files conditional | no tags | |
| file_metadata conditional | no tags | |
| sync_project conditional | no tags | |
| list_test_profiles conditional | no tags | |
| run_tests conditional | no tags | |
| test_status conditional | no tags | |
| queue_status conditional | no tags | |
| worker_status conditional | no tags | |
| job_status conditional | no tags | |
| cancel_job conditional | no tags | |
| get_test_log conditional | no tags | |
| cancel_test conditional | no tags | |
| list_services conditional | no tags | |
| service_status conditional | no tags | |
| start_service conditional | no tags | |
| stop_service conditional | no tags | |
| restart_service conditional | no tags | |
| list_backups conditional | no tags | |
| backup_database conditional | no tags | |
| request_action_approval conditional | no tags | |
| approval_status conditional | no tags | |
| migration_status conditional | no tags | |
| apply_migrations conditional | no tags | |
| start_migration_job conditional | no tags | |
| migration_job_status conditional | no tags | |
| plan_deploy conditional | no tags | |
| deploy_staging conditional | no tags | |
| deployment_status conditional | no tags | |
| list_releases conditional | no tags | |
| rollback_plan conditional | no tags | |
| rollback_release conditional | no tags | |
| rollback_status conditional | 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 digest58185c2324822be4
Scanned2026-10-15
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 0.1.3. Pin a release below and the command asks for exactly that one.
0.1.3
2 Oct 2026
latestNo release note was published with this version.
0.1.2
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 Runner 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.