Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

Juriset

PYPI · JURISET-MCP · 3 COMPONENTS

Verified, cited US and Canadian employment and payroll rules, each value with its official source.

+18 this week 75 Trust /100

Last scanned (15 hours ago)

Scores higher than 68% of PyPI servers

Category Finance and Payments

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →

Supply Chain Security100
  • No malware found by supply-chain analysis.Pass
  • No known CVEs affecting this package version or its production dependencies.Pass
  • No install/post-install scripts declared.Pass
  • 1 of 31 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency45
Schema Quality & AI Usability68
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 1792 tokens (~224/item across 8 items; 8 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management40
  • Stability observed for 12 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 8 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 8 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (16)

  • Malware scan
  • Known CVEs
  • Install scripts
  • Dependency health
  • Source repository
  • Provenance
  • License
  • Maintenance
  • Security disclosure
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this package (2)

  • Endpoint SecurityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.
  • Transport & ReachabilityScored on hosted endpoints only. A package has no live endpoint of its own for us to probe.

The score does not measure everything. What the score does not measure →

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 21 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 20 Nov 26 −15
    • Malware scan: pass → unverified ▼ security
  • 19 Nov 26 +16
    • Malware scan: unverified → pass ▲ security
  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Nov 26 +1
    • Package version: 0.1.2 → 0.1.3 functional
  • 12 Nov 26 +2
    • Stability: unverified → 0.10 ▲ functional
    • Package version: 0.1.0 → 0.1.2 functional
  • 9 Nov 26 54

    First indexed and scored.

Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 21 Nov 2026 · Analysed pypi/juriset-mcp@0.1.3

Provenance No attestation

The registry publishes no build provenance for this version, so there is nothing to verify.

Result No attestation
Ecosystem pypi
Reason No attestation published

Background: How many MCP packages publish verified provenance →

Dependencies 31 packages
Packages resolved 31
No linked repository 1
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 8 exposed · ~1,792 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
compare_jurisdictions ~271

Get one rule type across jurisdictions in one call, each entry in the same shape as get_rule. Example: `{"rule_type": "minimum_wage", "jurisdictions": ["us-wa", "us-or", "us-ca"]}`. Without `jurisdictions`, every state and province (or the `level` you name) is returned: about 3 KB each, 50+ entries. Entries are never merged or ranked. Informational only, not legal advice. `as_of` needs an API key whose plan includes as-of queries.

NameTypeReqDescription
as_ofstring–A date, `YYYY-MM-DD`, instead of today.
domainstring–The rule type's domain, e.g. `employment`. Optional: when omitted it is looked up from the rule type.
jurisdictionsarray–Up to 100 jurisdiction slugs, any level, e.g. `["us-wa", "us-or", "us-ca"]`. Not with `level`.
levelarray–Instead of `jurisdictions`: every jurisdiction at these levels, e.g. `["state", "province"]` (the default).
rule_typestringyesRule type slug from list_rule_types, e.g. `minimum_wage`.

No output schema declared.

No examples provided.

get_rule ~358

Get the rule in force today for one rule type in one jurisdiction, with its citation: source URL, verbatim excerpt and the snapshot Juriset stored. Example: `{"rule_type": "minimum_wage", "jurisdiction": "us-wa"}`. The response is the API's: `data` holds the values (described by the JSON Schema at `schema_url`), `effective_from` and `verified_at` date them, `id` is the version id to record with any decision that relies on it (see resolve_version), and `verification` says which models extracted and checked it and whether a person reviewed it. `verified_at` is when the sources were last re-fetched and found unchanged, not the review date (`verification.reviewed_at`); it is null until a newly fetched source has been re-checked once. Read `data` with its schema: optional fields carry defaults there, e.g. a `minimum_wage` tier or exception without `per_unit` is per hour. Where levels stack (e.g. US federal and state overtime) every level comes back as its own entry in `layers`; Juriset never merges them. Informational only, not legal advice (`disclaimer`).

NameTypeReqDescription
domainstring–The rule type's domain, e.g. `employment`. Optional: when omitted it is looked up from the rule type.
jurisdictionstringyesJurisdiction slug from list_jurisdictions, e.g. `us-wa` (Washington), `us` (US federal), `ca-ab` (Alberta).
rule_typestringyesRule type slug from list_rule_types, e.g. `minimum_wage`, `overtime`.

No output schema declared.

No examples provided.

get_rule_as_of ~245

Get the rule that was (or will be) in effect on a date, in the same shape as get_rule. Example: `{"rule_type": "minimum_wage", "jurisdiction": "us-wa", "as_of": "2025-06-30"}`. Use it to see what applied when a past decision was made. A date before Juriset's coverage of that jurisdiction is answered with an error that says where coverage starts. Informational only, not legal advice. If the API key's plan does not include as-of queries the error says so.

NameTypeReqDescription
as_ofstringyesThe date, `YYYY-MM-DD`, past or future.
domainstring–The rule type's domain, e.g. `employment`. Optional: when omitted it is looked up from the rule type.
jurisdictionstringyesJurisdiction slug from list_jurisdictions, e.g. `us-wa` (Washington), `us` (US federal), `ca-ab` (Alberta).
rule_typestringyesRule type slug from list_rule_types, e.g. `minimum_wage`, `overtime`.

No output schema declared.

No examples provided.

get_rule_history ~204

List every version ever published of one jurisdiction's rule, with its effective dates, values, citation and whether it is current, superseded or withdrawn. Example: `{"rule_type": "minimum_wage", "jurisdiction": "us-wa"}`. Covers that jurisdiction's own rule only; other levels that apply (e.g. `us`) are separate calls. Each entry's `id` can be passed to resolve_version. Informational only, not legal advice.

NameTypeReqDescription
domainstring–The rule type's domain, e.g. `employment`. Optional: when omitted it is looked up from the rule type.
jurisdictionstringyesJurisdiction slug from list_jurisdictions, e.g. `us-wa` (Washington), `us` (US federal), `ca-ab` (Alberta).
rule_typestringyesRule type slug from list_rule_types, e.g. `minimum_wage`, `overtime`.

No output schema declared.

No examples provided.

list_changes ~291

List changes to published rules, oldest first: new versions, amendments, corrections and repeals, each naming the rule, the versions moved from and to, the effective date and the version id to pass to resolve_version. Example: `{"since": "2026-10-01", "jurisdictions": ["us", "us-wa"]}`. Each jurisdiction matches its own rules only, so for everything that changes Washington's answer pass the federal level too. While `has_more` is true, call again with the response's `cursor`. Needs an API key whose plan includes the change feed; otherwise the error says so. Informational only, not legal advice.

NameTypeReqDescription
cursorstring–The `cursor` of the previous response, to continue or to poll for new changes.
domainstring–Only this domain, e.g. `employment`.
jurisdictionsarray–Jurisdiction slugs, e.g. `["us", "us-wa"]`; each matches its own rules only.
limitinteger–Changes per call, 1 to 500.
rule_typestring–Only this rule type, e.g. `overtime`.
sincestring–Where to start: an ISO 8601 date or date-time, e.g. `2026-10-01` (midnight UTC). Give this or `cursor`.

No output schema declared.

No examples provided.

list_jurisdictions ~153

List the US and Canadian jurisdictions Juriset covers, or find one by name. The other Juriset tools take slugs, not names. Each entry has the slug, name, level (`country`, `state`, `province`, `county` or `city`) and parent. Examples: `Washington` or `WA` → `us-wa`; `Alberta` → `ca-ab`; the federal levels are `us` and `ca`. Omit `query` for all of them. Reads the registry; no rule lookup.

NameTypeReqDescription
querystring–A name, postal abbreviation or slug, any case: `Washington`, `WA`, `us-wa`. Omit to list every jurisdiction.

No output schema declared.

No examples provided.

list_rule_types ~122

List the kinds of rule Juriset publishes. Each entry has its slug (the `rule_type` argument of the other tools), domain, description, how jurisdiction levels combine (`override`, `max` or `stack`) and the JSON Schema of its `data`, with every field described. Examples: `minimum_wage` and `overtime` (domain `employment`). Optional `domain` filter. Reads the registry; no rule lookup.

NameTypeReqDescription
domainstring–Only this domain's rule types, e.g. `employment` or `payroll`.

No output schema declared.

No examples provided.

resolve_version ~148

Get exactly the version a stored id names, forever, even after it was superseded or withdrawn: the values, effective dates, citation, verification record and its status today. Version ids (`rv_…`) come from the `id` of any rule response. Use it to re-check the value a decision relied on, or to show an auditor which rule applied. Example: `{"version_id": "rv_000000000000000000000000F2"}`. Informational only, not legal advice.

NameTypeReqDescription
version_idstringyesA version id from a rule response's `id`, e.g. `rv_000000000000000000000000F2`.

No output schema declared.

No examples provided.

Install

How do I install the Juriset MCP server?

Juriset runs locally as a PyPI package, launched with uvx juriset-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

pypi · juriset-mcp

# add to Claude Code
claude mcp add dev-juriset-juriset -- uvx juriset-mcp
Common questions

What is the Juriset MCP server?

Juriset is an MCP server listed in the public MCP registry as dev.juriset/juriset. Verified, cited US and Canadian employment and payroll rules, each value with its official source. This page covers its PyPI package (juriset-mcp).

Is the Juriset MCP server safe to use?

Juriset scores 75 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 21 November 2026. It declares no install or post-install scripts. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the Juriset MCP server expose?

Juriset exposes 8 tools: list_jurisdictions, list_rule_types, get_rule, get_rule_as_of, get_rule_history, and 3 more. Their descriptions and schemas cost roughly 1,792 tokens of context every time the server is loaded.

Is the Juriset MCP server still maintained?

Juriset is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What licence is the Juriset MCP server under?

Juriset declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

What did VerifyMCP test on the Juriset MCP server?

VerifyMCP ran 16 checks on Juriset, covering Malware scan, Known CVEs, Install scripts, Dependency health and 12 more. Endpoint Security and Transport & Reachability do not apply to a PyPI package, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.