Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
Nothing to run from here
Jobsite Safety Reference (free) 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
tool-list score
7
tools declared
remote
at its publisher
—
calls last 7d
What it does
Free, no-login construction safety tools: OSHA rule text, toolbox talks, 1904 recordability.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http jobsite-safety-reference-free-mcp https://jobsitecerts.com/api/mcp/public
# 2 — ask your agent for something these tools do
# lookup_jobsite_docs, search_articles, search_law_corpus and 4 more
Jobsite Safety Reference (free) costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JOAll 2 servers
jobsitecerts2 servers
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. Nothing here runs on your machine and nothing runs on ours: this server answers at its publisher’s own address, and what you install is the connection straight to it.
Claude Codedeclared by this listing
This is a public server: it answers at its publisher’s own address and this marketplace is not in the path. Claude Code registers it in one command; --scope user makes it available in every project. The transport below is http, as the publisher's own manifest declares it.
claude mcp add --scope user --transport http jobsite-safety-reference-free-mcp https://jobsitecerts.com/api/mcp/publicReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it answers at its publisher’s own address: 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 pointing straight at the publisher’s own address — this marketplace is not in the path, and nothing from this listing executes on your machine.
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.
Look up how Jobsite (this product) works — features, UI navigation, terminology, account / billing, worker-side experience, what counts as a 'group' vs 'crew', etc. Use this for any 'how do I…' / 'where do I find…' / 'what does X mean in Jobsite' question. Returns matching sections from the curated product guide. NOT for OSHA / regulatory questions (use search_law_corpus or search_training_source)
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural-language query, e.g. 'how do I add a worker', 'difference between groups and crews', 'where do I see expiring certs'. |
| limit | number | no | Max sections to return. Defaults to 4, cap 8. |
Search Jobsite's published marketing content — blog articles, head-to-head COMPETITOR COMPARISON pages (e.g. 'Jobsite vs Procore', 'Jobsite vs SiteDocs', 'Jobsite vs SafetyCulture'), and pillar guides. Use this whenever the user asks how Jobsite compares to a competitor ('how are you better than Procore', 'Jobsite vs SafetyCulture', 'why pick you over X'), or asks for a published article on a cons
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural-language query, e.g. 'how is Jobsite better than Procore', 'Jobsite vs SiteDocs', 'confined space article'. |
| limit | number | no | Max articles to return. Defaults to 4, cap 6. |
Search the VERBATIM authority corpus behind Jobsite's training: 29 CFR regulation text (per-section, with citations), the CA/WA/OR state rules for heat illness and wildfire smoke, plus OSHA interpretations and NIOSH/CDC/EPA technical guidance the training cites. Use this when the user asks what an authority ACTUALLY SAYS — exact rule language, a specific citation ('what does 1926.501 require'), tr
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Plain-words regulatory question or a citation number — 'fall protection trigger height', '1926.501', 'silica exposure control plan'. |
| jurisdiction | string | no | Optional filter. Omit to search all jurisdictions (federal is most of the corpus). |
| limit | number | no | Max sections to return. Defaults to 4, cap 8. |
Search recent regulatory / safety news from the Federal Register (filtered to OSHA) and the OSHA news RSS feed. Use for questions about recent rule changes, enforcement memos, or news that might affect a training course's content (e.g. 'any silica updates this year', 'recent fall protection rulemaking'). Returns titles, agencies, dates, URLs, and short summaries — pure pass-through, nothing is per
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | Natural-language search terms. Best with topical keywords plus standard numbers when known. |
| limit | number | no | Max results to return per source. Defaults to 6, cap 12. |
Runs Jobsite's deterministic OSHA 29 CFR 1904 decision tree on the facts of an injury or illness: returns the proposed 300-log classification (or the questions still needed), the rationale with verbatim 1904 quotes, and any report-to-OSHA deadline (8 or 24 hours). Map the story to the answers; leave out anything not known — unknowns come back as questions, never guesses. Reads and writes no record
| Parameter | Type | Required | Notes |
|---|---|---|---|
| work_environment_event | boolean | no | An event or exposure at work caused or contributed. |
| exception | string | no | A 1904.5(b)(2) work-relatedness exception, or none. |
| new_case | boolean | no | A new case, not a recurrence of one already recorded. |
| death | boolean | no | — |
| days_away | boolean | no | ≥1 calendar day away after the day of injury (taken or recommended). |
| restricted_or_transferred | boolean | no | Restricted work or job transfer beyond the day of injury. |
| treatments | array | no | Every care given ([] = none). First-aid items are the closed 1904.7(b)(5)(ii) list; anything else is medical treatment. |
| loss_of_consciousness | boolean | no | — |
| significant_diagnosis | boolean | no | Cancer, chronic irreversible disease, fractured/cracked bone or punctured eardrum, diagnosed by a clinician. |
| inpatient_hospitalization | boolean | no | Formal in-patient admission for care (not observation only). |
| amputation_or_eye_loss | boolean | no | Amputation (incl. a fingertip) or loss of an eye. |
A ready-to-deliver construction toolbox talk from Jobsite's library of nearly 300 talks, in English or Spanish: title, talking points, a discussion question, duration, and the OSHA standards it is built on. Find one by topic or hazard in plain words ("trenching", "heat", "ladder setup") or by standard number ("1926.501"), or fetch one by talk_number. Returns the best match plus up to five other ma
| Parameter | Type | Required | Notes |
|---|---|---|---|
| topic | string | no | The hazard, task or standard, e.g. "trench cave-ins", "silica", "1926.1053". |
| talk_number | integer | no | Or one talk by its number (from other_matches). |
| language | string | no | en (default) or es (Spanish). |
Create a new Jobsite workspace that holds only sample data (a sample crew, jobs and safety records; nothing real) for the person you are helping, so they can try Jobsite without setting anything up. Returns a one-time claim link to give them: opening it lets them create their login (or sign in) and own the workspace. The link expires in 7 days, and an unclaimed workspace is then deleted. Exploring
| Parameter | Type | Required | Notes |
|---|---|---|---|
| company_name | string | no | The company name for the workspace (default "Sample Company"). The person can change it later. |
| focus | string | no | safety (default): the Safety Suite. home_services: the Home Services Suite (service calls, estimates). |
| trade | string | no | The company's trade in a few words, e.g. "roofing" or "HVAC"; it sets the workspace's industry when it matches one Jobsite lists. |
Free
$0 forever
- Every tool — any call limit is its publisher’s, not ours
- No card, and mcprush charges nothing for it
- Runs at its publisher’s own address — this marketplace is not in the path
- 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 Jobsite Safety Reference (free) 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: —
ATool-list grade · score 93 / 100
Release 1.0.0 · scanned 31 Oct 2026
Graded from the tools this server lists, not from its source code.
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
Findings0 threat · 0 capability
Capabilitymoderate
Coveragemanifest
Verificationnot in this report
Surface digeste3343127485b29119a8e6b90759c8e22ee5e7f8a82e931b38ef8b7b8a7c43b29
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| coverage-honesty | manifest | inspection depth (manifest) — how much of the target the scan could see | −4 |
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.
The scan read each tool’s name, description, input schema and annotations exactly as the server listed them the last time it answered us; no code was reviewed. We ask the server again about once a month, and a list that changed is graded again.
Tool surfaceread
Implementation sourcenot available
Package metadatanot available
Live transportnot available
The implementation source was not read — this reflects the declared tool metadata only.
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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| lookup_jobsite_docs | no tags | |
| search_articles | no tags | |
| search_law_corpus | no tags | |
| search_regulatory_news | untrusted-input | untrusted-input: keyword "rss", declares openWorldHint: true (interacts with entities outside the server) |
| osha_recordability_check | no tags | |
| get_toolbox_talk | untrusted-input | untrusted-input: keyword "fetch" |
| start_jobsite_workspace | state-write | state-write: declares readOnlyHint: false |
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 digeste3343127485b2911
Scanned2026-10-31
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
This is an address its publisher runs: which release it serves is theirs to choose, so there is nothing here to pin. The history below is for reading; the current release on file is 1.0.0.
1.0.0
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 Jobsite Safety Reference (free) 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.