Comprehensive Model Context Protocol server for managing Home Assistant through AI assistants.
FRTracker — Federal Regulatory Research 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
Source-linked US federal regulations: CFR provision history, obligations, rules, comments.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user --transport http frtracker-federal-regulatory-research-mcp https://frtracker.app/mcp
# 2 — ask your agent for something these tools do
# lookup_provision, get_provision_history, rules_amending and 7 more
FRTracker — Federal Regulatory Research costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
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.
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 frtracker-federal-regulatory-research-mcp https://frtracker.app/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
10 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 a CFR provision by citation (e.g. "21 CFR 1304.04") or by an exact quotation, optionally as of a past date. Returns the provision text with a ProvisionEvidence object (source, snapshot date, hashes). Explicitly reports ambiguity or no-match instead of guessing. Requires a free API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Citation ("21 CFR 1304.04") or an exact quote from regulatory text |
| as_of | string | no | Optional YYYY-MM-DD snapshot upper bound (not in the future) |
Documented change history for a CFR provision by canonical id (e.g. "21-cfr-1304.04(a)"): before/after text, computed redline, observed dates, and candidate final rules. 404 when the provision is not in the documented-change set — absence of a documented change is not a claim that nothing changed. No API key required.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| canonical_id | string | yes | Canonical provision id, e.g. "21-cfr-1304.04(a)" |
Which final rules amend a CFR part or section, read from each rule's own amendatory instructions ("Amend § 52.2120 by..."). Returns the rules, the sections each addresses, and dates. This reports what a rule SAYS it amends — it is not an attribution of any observed text change to that rule. Covers 2020-present; absence means not indexed, not that no rule amended it. No API key required.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| title | string | yes | CFR title number, e.g. "40" |
| part | string | yes | CFR part, e.g. "52" |
| section | string | no | Optional section id, e.g. "52.2120". Omit for all rules touching the part. |
| limit | integer | no | Max rules (default 50, max 200) |
Most recent detected changes to CFR text (title, part, name, dates), newest first. No API key required.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| limit | integer | no | Max rows (default 50, max 200) |
Aggregate corpus statistics: documents, obligations, pairs, agencies, coverage dates. No API key required.
No parameter schema on file.
Full-text search over Federal Register documents and extracted obligations (FTS5/BM25). Totals are approximate (total_exact: false). Requires an API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| q | string | yes | Search query (min 3 chars) |
| tab | string | no | Result type (default all) |
| limit | integer | no | Max results (default 25, max 50) |
| page | integer | no | Page number (default 1) |
List Federal Register documents with filters: agency slug, document type, rulemaking pathway (interim_final/temporary/direct_final = notice-and-comment bypass classes), or docket id. Requires an API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agency | string | no | Agency slug, e.g. "environmental-protection-agency" |
| type | string | no | Document type |
| pathway | string | no | Rulemaking pathway |
| docket | string | no | Docket id |
| limit | integer | no | Max rows (default 25, max 100) |
| page | integer | no | Page number (default 1) |
List extracted regulatory obligations ("who must do what") with filters: agency, deontic class, free text. Obligations are machine-extracted with quality tiers; they are not legal advice. Requires an API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| agency | string | no | Agency slug |
| deontic | string | no | Deontic class |
| q | string | no | Full-text filter within obligations |
| limit | integer | no | Max rows (default 25, max 100) |
| page | integer | no | Page number (default 1) |
Detail for one extracted obligation by id, including its source rule and citation URL. Requires an API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| id | string | yes | Requirement id |
Public comments for a Federal Register document (organization, title, date, body where available). Coverage is partial and stated in the response. Requires an API key.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| doc | string | yes | Federal Register document number, e.g. "2024-12345" |
| offset | integer | no | Row offset for pagination |
- 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 FRTracker — Federal Regulatory Research 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.
This listing is an address its publisher runs, and you connect to it directly — this marketplace is not in the path. The scanner reads packages and public source, and an address is neither. So there is no grade — not a withheld one, an unmeasured one.
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.
No release note was published with this version.
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 FRTracker — Federal Regulatory Research 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.