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.

EveryAILaw

NPM · EVERY-AI-LAW · SCANNED SEP 22

AI law obligations, evidence, deadlines, saved profiles, audit trails, and signed change alerts.

Available components

0 this week 76 Trust /100
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
  • No production dependencies, so there is no dependency health to assess. View diagnostics → Pass
Provenance & Transparency6
Schema Quality & AI Usability78
  • AI-judged instruction clarity (excellent).Pass
  • Tool/resource definitions use about 1106 tokens (~55/item across 20 items; 20 tools + 0 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management93
  • Stability observed for 28 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 20 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 20 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
Install

How do I install the EveryAILaw MCP server?

EveryAILaw runs locally as an npm package, launched with npx -y every-ai-law. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

npm · every-ai-law

# add to Claude Code
claude mcp add snapsynapse-every-ai-law -- npx -y every-ai-law
// .cursor/mcp.json
{
  "mcpServers": {
    "snapsynapse-every-ai-law": {
      "command": "npx",
      "args": [
        "-y",
        "every-ai-law"
      ]
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "snapsynapse-every-ai-law": {
      "command": "npx",
      "args": [
        "-y",
        "every-ai-law"
      ]
    }
  }
}
# add to Codex CLI
codex mcp add snapsynapse-every-ai-law -- npx -y every-ai-law
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "snapsynapse-every-ai-law": {
      "type": "local",
      "command": [
        "npx",
        "-y",
        "every-ai-law"
      ],
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add snapsynapse-every-ai-law --command npx --arg -y --arg every-ai-law
# ~/.hermes/config.yaml
mcp_servers:
  snapsynapse-every-ai-law:
    command: "npx"
    args: ["-y", "every-ai-law"]
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "snapsynapse-every-ai-law": {
      "Transport": "stdio",
      "Command": "npx",
      "Arguments": [
        "-y",
        "every-ai-law"
      ]
    }
  }
}
# add to Vellum
assistant mcp add snapsynapse-every-ai-law -t stdio -c npx -a -y every-ai-law
// mcp.json
{
  "mcpServers": {
    "snapsynapse-every-ai-law": {
      "command": "npx",
      "args": [
        "-y",
        "every-ai-law"
      ]
    }
  }
}
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 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 83. That category is still filling its 30-day observation window: 24 days of observed history at the previous scan, 25 at this one. The score rises as the window fills, whether or not the server changes.

  • 18 Sept 26 −3
    • Stability: pass → 0.80 functional
    • Package version: 0.6.0 → 0.9.2 functional
  • 17 Sept 26 0
    • Stability: 0.97 → pass security
  • 16 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 93 to 97. That category is still filling its 30-day observation window: 28 days of observed history at the previous scan, 29 at this one. The score rises as the window fills, whether or not the server changes.

  • 14 Sept 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 87 to 90. That category is still filling its 30-day observation window: 26 days of observed history at the previous scan, 27 at this one. The score rises as the window fills, whether or not the server changes.

  • 13 Sept 26 +15
    • Malware scan: unverified → pass security
  • 12 Sept 26 −17
    • Stability: pass → unverified security
    • Malware scan: pass → unverified security
    • Tool safety: pass → unverified security
    • Capabilities: pass → unverified functional
    • Tool coverage: 100 → unverified functional
    • Stability: pass → 0.83 functional
    • Package version: 0.9.0 → 0.9.2 functional
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 22 Sept 2026 · Analysed npm/every-ai-law@0.9.2

Provenance No attestation

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

Result No attestation
Ecosystem npm

Background: How many MCP packages publish verified provenance →

Dependencies 0 packages
Packages resolved 0
Tree resolution Complete

Background: SBOMs and build attestations, explained →

MCP tools · 20 exposed · ~1,106 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
check_requirement ~64

Check whether the pinned EveryAILaw corpus maps a regulation to a specific obligation category. The backward-compatible required boolean reports that modeled mapping, not legal applicability or a complete no-duty conclusion.

NameTypeReqDescription
obligationstringyesObligation ID
regulationstringyesRegulation ID

No output schema declared.

No examples provided.

compare_regulations ~47

Compare two regulations by obligation overlap. Explicit regulation IDs may include terminal historical instruments.

NameTypeReqDescription
regulation_astringyesFirst regulation ID
regulation_bstringyesSecond regulation ID

No output schema declared.

No examples provided.

custom_matrix ~72

Build a sparse obligation-by-instrument evidence matrix for a saved Pro profile. Missing cells mean not represented in the corpus, not no legal obligation or compliance.

NameTypeReqDescription
obligationsarrayOptional obligation IDs to include. Omit for all obligations.
profile_idstringyesSaved EveryAILaw Pro profile ID.

No output schema declared.

No examples provided.

find_regulations_by_obligations ~44

Find current regulations that address ALL specified obligations. Terminal historical instruments are excluded.

NameTypeReqDescription
obligationsarrayyesArray of obligation IDs that must ALL be addressed

No output schema declared.

No examples provided.

get_audit_log ~63

Retrieve the authenticated customer's append-only EveryAILaw Pro tool-event history. Raw tool arguments and API keys are never returned or stored.

NameTypeReqDescription
limitnumberMaximum events to return, from 1 to 100. The Pro API bounds out-of-range values.

No output schema declared.

No examples provided.

get_authority ~28

Get full details for a regulatory authority by ID.

NameTypeReqDescription
idstringyesAuthority ID

No output schema declared.

No examples provided.

get_evidence ~29

Get verification sources and freshness dates for a provision.

NameTypeReqDescription
provision_idstringyesProvision ID

No output schema declared.

No examples provided.

get_obligation ~57

Get full details for an obligation by ID, including which current regulations address it. Terminal historical instruments are excluded from this aggregate.

NameTypeReqDescription
idstringyesObligation ID (e.g. "transparency", "human-oversight")

No output schema declared.

No examples provided.

get_provision ~81

Read a stored provision by its local slug, including complete current requirement and penalty rows, official source locator, Obligation First links, and qualified dates. No historical as-of lookup or organization-specific applicability determination.

NameTypeReqDescription
idstringyesProvision ID returned by get_regulation (e.g. "eu-ai-act-literacy"), not an Obligation First URI.

No output schema declared.

No examples provided.

get_regulation ~67

Get regulation metadata, timeline, provision IDs and obligations covered. Use get_provision with a returned provision ID for its complete stored requirements, penalties and source locator.

NameTypeReqDescription
idstringyesRegulation ID (e.g. "eu-ai-act", "colorado-sb24-205")

No output schema declared.

No examples provided.

get_staleness_report ~40

Get provisions whose verified date exceeds a threshold. Default 30 days.

NameTypeReqDescription
threshold_daysnumberDays threshold (default: 30)

No output schema declared.

No examples provided.

get_timeline ~42

Get upcoming enforcement dates and milestones across current regulations. Terminal historical instruments are excluded.

NameTypeReqDescription
afterstringShow dates after this ISO date (default: today)

No output schema declared.

No examples provided.

list_authorities ~20

List all regulatory bodies with their jurisdictions and regulation counts.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_obligations ~26

List all tracked compliance obligations with IDs, names, groups, and provision counts.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

list_regulations ~72

List current tracked regulations by default. Optionally filter by jurisdiction or status; an explicit terminal status returns historical records.

NameTypeReqDescription
jurisdictionstringFilter by jurisdiction (e.g. "EU", "California")
statusstringFilter by status (e.g. "enforcing", "enacted")

No output schema declared.

No examples provided.

list_standards ~18

List all voluntary and harmonized standards.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

query_with_profile ~52

Deterministically filter current EveryAILaw instruments by a saved Pro profile. This is corpus filtering, not legal advice or an applicability determination.

NameTypeReqDescription
profile_idstringyesSaved EveryAILaw Pro profile ID.

No output schema declared.

No examples provided.

save_profile ~130

Create or update a customer-scoped EveryAILaw Pro jurisdiction and role profile. A profile is filtering input, not a legal applicability determination.

NameTypeReqDescription
idempotency_keystringStable retry key required when creating a profile. Reuse it after an uncertain response.
jurisdictionsarrayyesEveryAILaw jurisdiction slugs.
namestringyesHuman-readable profile name.
profile_idstringExisting profile ID to update. Omit to create a profile.
rolesarrayEveryAILaw role slugs. An empty list means all roles in the saved jurisdictions.

No output schema declared.

No examples provided.

search ~29

Search across obligations, regulations, provisions, and authorities by keyword.

NameTypeReqDescription
querystringyesSearch query

No output schema declared.

No examples provided.

subscribe_to_changes ~125

Manage informational HTTPS webhook subscriptions for deterministic EveryAILaw corpus changes. Registration returns a signing secret once and requires endpoint challenge verification.

NameTypeReqDescription
actionstringyesOne of: list, register, verify, rotate_secret, remove.
endpoint_idstringWebhook endpoint ID for verify, rotate_secret, or remove.
filtersobjectOptional exact filters: jurisdictions, roles, obligations, and change_types.
profile_idstringSaved Pro profile ID for registration.
urlstringPublic HTTPS webhook URL on port 443 for registration.

No output schema declared.

No examples provided.

Common questions

What is the EveryAILaw MCP server?

EveryAILaw is an MCP server listed in the public MCP registry as io.github.snapsynapse/every-ai-law. AI law obligations, evidence, deadlines, saved profiles, audit trails, and signed change alerts. This page covers its npm package (every-ai-law).

Is the EveryAILaw MCP server safe to use?

EveryAILaw scores 76 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 22 September 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 EveryAILaw MCP server expose?

EveryAILaw exposes 20 tools: list_obligations, get_obligation, list_regulations, get_regulation, get_provision, and 15 more. Their descriptions and schemas cost roughly 1,106 tokens of context every time the server is loaded.

Is the EveryAILaw MCP server still maintained?

EveryAILaw is still listed as active in the MCP registry. We last reached this channel on 22 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.