Local MCP capabilities provider for Expo
SLF Guardian 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.
What it does
SLF Guardian adds six evidence-backed checks to a coding agent workflow, before it acts: check_package checks PyPI/npm dependencies before installation; check_command reviews shell/SQL before execution; audit_code examines source before delivery; check_prompt looks for instruction injection in untrusted text; check_domain checks a domain before opening; scan_site performs a passive outside-in check only for sites you own or are authorized to test. Results are pass, warn, review or block with findings; a pass is not proof of safety. The MCP server runs locally over stdio and calls SLF Guardian API. No submitted code or command is executed. Each API key starts with 1,000 free calls; subsequent calls cost $0.01 each. Rate limit: 20 calls per minute. The host agent must call the tool and honor its result; SLF Guardian is a policy signal, not an enforcement layer.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --env 'SLF_API_KEY=${SLF_API_KEY}' --transport stdio slf-guardian-mcp '--' uvx slf-guardian-mcp
# 2 — ask your agent for something these tools do
# audit_code, check_package, check_prompt and 3 more
It needs SLF_API_KEY: this reads it from your environment, so export it first.
SLF Guardian costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
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 SLF Guardian 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 is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. Claude Code reads SLF_API_KEY (SLF Guardian API key (slf_live_...). Get one free: POST https://slfguardian.com/v1/keys) from your environment each time it starts the server, so the value stays out of its config: export it in your shell profile (macOS, Linux), or run setx SLF_API_KEY … and open a new terminal (Windows). The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user --env 'SLF_API_KEY=${SLF_API_KEY}' --transport stdio slf-guardian-mcp '--' uvx slf-guardian-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
It reaches a system of yours, so it needs your own credential rather than the publisher’s: SLF_API_KEY — SLF Guardian API key (slf_live_...). Get one free: POST https://slfguardian.com/v1/keys. You set it in your own client’s config, on your machine — this marketplace never holds it.
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.
6 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.
Audit source code before delivering or running it. Flags remote code execution (curl | bash), data exfiltration of environment variables or credential files, reverse shells, destructive commands, hidden base64 payloads, hard-coded secrets (AWS, OpenAI, Stripe, GitHub, database URLs), install-time…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| code | string | no | Source code to audit (single file or snippet). |
| path | string | no | Optional file name for the snippet. |
| files | array | no | Several files instead of one snippet. |
Check a PyPI or npm package before installing or recommending it. Asks the registry whether the name exists at all (invented package names are how slopsquatting attacks land), how old it is, how much it is downloaded, whether it runs install scripts, whether it is deprecated or yanked, whether OSV…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| ecosystem | string | no | — |
| name | string | no | Package name. |
| version | string | no | Optional exact version to check. |
| packages | array | no | Check several packages in one call. |
Check untrusted text, HTML or a web page for prompt injection before feeding it to a model. Finds instructions written for the model instead of the reader: text hidden with CSS, HTML comments, zero-width and invisible Unicode tag characters, chat template markers, 'ignore previous instructions',…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| text | string | no | Plain text to check. |
| html | string | no | HTML including hidden markup. |
| url | string | no | Public page to fetch and check. |
Check a shell command or SQL statement before running it and say whether it can be undone. Flags recursive and system-path deletes, disk writes, history and credential wiping, firewall changes, force push and hard reset, docker volume and kubernetes deletes, terraform destroy, cloud bucket and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| command | string | no | Command or statement to check. |
| kind | string | no | Defaults to auto. |
| commands | array | no | Check a sequence in one call. |
Check a domain or link before opening it, sending data to it or installing from it. Uses the public registration record and DNS: registration age, registry status, whether it resolves, lookalike and typo-squatted brand names, a brand hidden in a subdomain, punycode and mixed-script hostnames, link…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | no | Domain or full URL. |
| domains | array | no | Check several in one call. |
Passive outside-in security check of a website: malware and spam injection traces, hidden redirects, SSL/TLS certificate state, security headers, exposed software versions and SPF/DMARC email spoofing protection. Does not log in, does not run attack tests. Returns a score out of 100, a grade and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| domain | string | yes | Domain or URL, e.g. example.com |
- 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 SLF Guardian or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | minimal | capability blast radius (minimal) — client exposure if the model is manipulated | −0 |
| 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 |
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.
No tools were enumerated, so prompt-injection, capability and toxic-flow analysis had no tool surface to inspect. To grade a package’s real runtime tools, 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. minimal is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| No per-tool rows for this release — see the note below. | ||
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
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 1.2.2. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- Aligns this listing with PyPI 1.2.1: stricter input validation and clearer credit, payment, and rate-limit guidance; the six tools remain unchanged.
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.
Any signed-in account that does not publish SLF Guardian can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.