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.

Washington Code

REMOTE · GATEWAY.PIPEWORX.IO · 2 COMPONENTS

Washington state law: the Revised Code of Washington (RCW, statutes), the Washington…

+4 this week 78 Trust /100

Last scanned (13 hours ago)

Scores higher than 76% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Education and Research

Recent critical change

Authorization (4 Nov 2026). See the changelog before you install this server.

Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security81
Transport & Reachability100
Schema Quality & AI Usability83
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 25370 tokens (~469/item across 54 items; 54 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Tools include usage examples.Pass
Stability & Change Management33
  • Stability observed for 10 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
  • Structured output schemas are declared (6% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 55 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities40
  • Spec-recency check failed: implements MCP spec 2025-03-26; the latest is 2026-07-28. See how to fix → Fail
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

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.

  • 5 Nov 26 +15
    • Authorization: fail → pass ▲ security
    • Stability: fail → 0.33 functional
  • 4 Nov 26 −14
    • Authorization: pass → fail ▼ critical
    • Stability: 0.27 → fail ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads security
    • Tool “deep_research” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads security
  • 3 Nov 26 +15
    • Authorization: fail → pass ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads security
    • Tool “deep_research” rewrote its description, which is the text the model reads security
    • Stability: fail → 0.27 functional
  • 2 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ask_pipeworx” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads security
    • Tool “deep_research” rewrote its description, which is the text the model reads security
  • 1 Nov 26 −13
    • Authorization: pass → fail ▼ critical
    • Stability: 0.17 → fail ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “deep_research” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads security
  • 31 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ask_pipeworx” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads security
    • Tool “deep_research” rewrote its description, which is the text the model reads security
  • 30 Oct 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “deep_research” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads security
    • Tool “compare_entities” rewrote its description, which is the text the model reads security
  • 29 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ask_pipeworx” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_beta” rewrote its description, which is the text the model reads security
    • Tool “ask_pipeworx_grounded” rewrote its description, which is the text the model reads security
    • Tool “bet_research” rewrote its description, which is the text the model reads security
    • Tool “deep_research” rewrote its description, which is the text the model reads security
    • “bet_research” reworded the description of “market” cosmetic
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 5 Nov 2026 · Probed https://gateway.pipeworx.io/washington-code/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=pipeworx.io CN=WE1,O=Google Trust Services,C=US 19 Sept 2026 18 Dec 2026 ECDSA 256 ECDSA-SHA256 907077ac952af983139424aa9b807ef7
SANs: pipeworx.io, gateway.pipeworx.io, *.gateway.pipeworx.io
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of gateway.pipeworx.io. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
io. DS published 38690 8 Verified
pipeworx.io. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://gateway.pipeworx.io/.well-known/oauth-protected-resource/washington-code/mcp" scope="pipeworx:read"

Bearer resource_metadata="https://gateway.pipeworx.io/.well-known/oauth-protected-resource/washington-code/mcp" scope="pipeworx:read"

Protected resource metadata

Document https://gateway.pipeworx.io/.well-known/oauth-protected-resource/washington-code/mcp
Retrieved Yes
Resource https://gateway.pipeworx.io/washington-code/mcp
Authorisation server https://gateway.pipeworx.io

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://gateway.pipeworx.io/washington-code/mcp Verified 200
http (plaintext) http://gateway.pipeworx.io/washington-code/mcp Served over HTTP 200
MCP tools · 54 exposed · ~25,138 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
suggest_questions ~240

What can I ask Pipeworx? / what is Pipeworx good for? / what can you do? / give me ideas / show me examples / getting started / what data do you have? — the onboarding entry point for an agent that just connected and wants to know what is worth asking. Returns category-bucketed example questions (company financials, drugs & clinical trials, economics, real estate, prediction markets, weather, government & patents, science & academia, news) — each with the exact tool + argument shape that answers it, drawn from the live catalog of thousands of tools. Call with no arguments for the full spread, or pass `topic` (e.g. "finance", "pharma", "betting") to focus. Use this FIRST when you do not yet know what Pipeworx can do for you, or to learn how to call the meta-tools (ask_pipeworx, entity_profile, compare_entities, etc.).

NameTypeReqDescription
topicstring–Optional focus area: finance | pharma | economics | real-estate | betting | weather | government | science | news. Omit for a cross-category spread.

No output schema declared.

{"topic":"finance"}
unsubscribe ~60

Cancel a subscription by id. Ownership is enforced — you can only cancel your own subscriptions. The row is deactivated (not deleted) so its historical events stay available via recent_alerts.

NameTypeReqDescription
idstringyesSubscription id (uuid) returned by subscribe.

No output schema declared.

No examples provided.

updown_divergence_rate ~586

How often two venues settled the SAME 15-minute crypto window differently, over every settled window on record. Compares polymarket.com (Chainlink TWAP) with Kalshi and with Polymarket US (both CF Benchmarks BRTI), and Kalshi with Polymarket US as the same-feed control. Per pair: windows both venues settled, divergent count, the rate with its 95% Wilson interval (withheld under 30 paired windows), which direction they split, and what was excluded (unsettled on a side, 50-50). A HEADLINE RATE IS A CONCENTRATION QUESTION, so every pair also carries `concentration` (UTC days and hours the divergent windows fell in, the busiest day, the top-3-day share, and a plain reading) and `by_how_decided` (the rate by how far the reference venue's mid was from 50 at its last priced minute: the rate is a fraction of a percent for windows that were decided by the end and tens of percent for the ones that were not). `divergent_path` gives the mean Up mid by minute on both venues over the divergent windows only, split by who said Up, so the "early spike that fades" story can be checked rather than assumed. Measured on the archive 2026-10-27 over 30 days of btc: polymarket.com vs Kalshi diverged on 48 of 2,847 windows (1.69%, interval 1.27-2.23), spread over 27 of 31 UTC days, 0.19% of windows decided by the end and 17-29% of the ones still undecided; Polymarket US vs Kalshi on 0 of 1,838. asset btc | eth | sol | xrp | bnb (bnb has no pair: Kalshi only); days 1-90 (default 30), capped by what the archive holds (it starts 2026-09-22 for polymarket.com and Kalshi, 2026-10-07 for Polymarket US). Read-only; cheap enough to call, it reads several thousand archive rows.

NameTypeReqDescription
assetstring–btc (default) | eth | sol | xrp | bnb. The archive holds btc/eth on all three venues, sol/xrp on polymarket.com and Polymarket US, bnb on Kalshi only (no pair).
daysnumber–Look-back in days, 1-90 (default 30). The archive starts 2026-09-22 (polymarket.com, Kalshi) and 2026-10-07 (Polymarket US, btc), so a longer span is capped by what is held; coverage is reported per…

No output schema declared.

{"asset":"btc","days":30}
{"asset":"eth","days":14}
updown_venue_compare ~719

The same 15-minute crypto "up or down" window priced on polymarket.com, Polymarket US and Kalshi, side by side, with whether each pair is actually the same contract. Pass asset (btc | eth | sol | xrp | bnb) and window ("current" default, "next", "previous", or the window START as ISO such as 2026-10-27T14:15:00Z, on a 15-minute boundary). Per venue: question, Up bid / ask / mid / last, spread_pp, quote_state, volume WITH ITS UNIT, open interest, liquidity, settlement source, comparison basis, when it settles. THE VENUES ARE NOT ONE CONTRACT. Kalshi and Polymarket US settle on CF Benchmarks' BRTI (60-second average at the end against the same at the start): the same bet, so a gap between them is a real disagreement. polymarket.com settles on a Chainlink 60-second TWAP, end against start: same comparison shape, different feed, so a gap against either is partly the contract. `pairs[]` gives equivalent ("true"|"false"|"unclear"|"not_comparable") from resolution_diff for every pair, material_differences, mid_diff_pp (a minus b, in percentage points) and read_as in words. Measured over 30 days of settled windows the Chainlink and BRTI feeds settle a window differently about 1.2-1.8% of the time, almost entirely windows that ended near the threshold (see updown_divergence_rate). `net_spread` is computed only for the pair that is equivalent: the gap in mid terms and at top of book (buy Up where cheaper at the ask, Down where Up is dearer at 1 minus the bid) after BOTH venues' taker fees, each fee carrying its verified-as-of date. Top-of-book size is shown where the venue publishes it (Polymarket US); the Kalshi figure is not in its market payload, so read its order book before sizing. A venue with no market for the window is {status:"not_listed", reason}; one that could not be read is {status:"unavailable", refusal} -- never an empty object, and never the same thing. A one-sided book (typical Polymarket US just before a window is decided) has quote_state "bid_only", a null…

NameTypeReqDescription
assetstring–btc (default) | eth | sol | xrp | bnb. Coverage differs by venue; a venue that does not list the asset answers not_listed.
horizonstring–15m (default and the only value offered).
windowstring–"current" (default), "next", "previous", or the window START as an ISO-8601 timestamp on a 15-minute boundary, e.g. 2026-10-27T14:15:00Z. An unaligned timestamp is refused, not rounded.

No output schema declared.

{"asset":"btc","horizon":"15m","window":"current"}
{"asset":"eth","window":"previous"}
{"asset":"btc","window":"2026-10-27T14:30:00Z"}
validate_claim ~370

"Is it true that…" / "fact check" / "verify the claim that…" / "did X really…" / "was Y actually…" / "confirm or refute" / "true or false" — natural-language claim verification against authoritative sources. Use whenever the agent needs to check whether something a user said is factually correct. Company-financial claims (revenue, net income, cash for public US companies) verify via the structured SEC EDGAR + XBRL fast path with exact percent-delta math; ANY OTHER factual claim (macro statistics, rates, prices, drug data, records) automatically falls through to the grounded pipeline — routed to the right live source, answered with verbatim evidence, then judged. Returns a verdict (confirmed / approximately_correct / refuted / inconclusive / unsupported / could_not_verify), the grounded or structured actual value with pipeworx:// citation, and reasoning. IMPORTANT for callers: could_not_verify means the check did not happen (our LLM or source failed) and carries verification_error{stage,detail} — it is NOT evidence for or against the claim, and must not be shown as one. unsupported means we looked and cover no source for it. Replaces 4–6 sequential calls (NL parsing → entity resolution → data lookup → comparison).

NameTypeReqDescription
claimstringyesNatural-language factual claim, e.g., "Apple's FY2024 revenue was $400 billion" or "Microsoft made about $100B in profit last year".
tolerance_pctnumber–Max percent deviation still graded approximately_correct (0.5–50). Overrides the tolerance implied by the claim wording — set 1–2 for hallucination detection where any material error must be refuted.…

No output schema declared.

{"claim":"Apple's fiscal 2023 revenue was $383 billion"}
wa_bill_amendments ~218

List the AMENDMENTS proposed to a Washington State legislative bill — amendment name/drafting number, sponsor (member or committee), type (floor/committee), description, floor action (ADOPTED/FAILED/WITHDRAWN) and date, with links to the amendment text. Returns the most recent amendment first and a count by floor action. Reads directly from the Washington State Legislature's own bill-tracking service. Use for "what amendments have been offered to HB 1002", "was the striker amendment adopted on SB 5016". A bill with no amendments on file returns an empty list, not an error. Keyless. For the bill's overall status use wa_bill_status.

NameTypeReqDescription
bienniumstring–Washington biennium, e.g. "2025-26" or a year like "2026". Omit for the current biennium.
billstringyesBill number, with or without prefix: "HB 1002", "SB 5016", or bare "1002".

No output schema declared.

{"biennium":"2023-24","bill":"1002"}
wa_bill_status ~244

Get the current status of a Washington State LEGISLATIVE BILL — its description, legal title, sponsor(s), introduced date, procedural history line and current status (e.g. "H Rules X", "Passed Legislature"), and companion bills in the other chamber. Reads directly from the Washington State Legislature's own bill-tracking service (not a third-party aggregator). Use for "what is the status of HB 1000", "who sponsored SB 5016", "is HB 1002 still active". Bill numbers reset each biennium (default: the current one) — pass biennium for a past session. Keyless. For an amendment history use wa_bill_amendments; for floor votes use wa_bill_votes; for everything introduced in a session use wa_session_bills.

NameTypeReqDescription
bienniumstring–Washington biennium, e.g. "2025-26" or a year like "2026". Omit for the current biennium.
billstringyesBill number, with or without prefix: "HB 1000", "SB 5016", "2SHB 1000", or bare "1000".

No output schema declared.

{"bill":"HB 1002"}
{"biennium":"2025-26","bill":"1000"}
wa_bill_votes ~184

Get the recorded FLOOR ROLL-CALL VOTES on a Washington State legislative bill — chamber, motion ("3rd Reading & Final Passage"), date, and yea/nay/absent/excused counts with the voting legislators named in each category. Most recent vote first. Reads directly from the Washington State Legislature's own bill-tracking service. Use for "how did the House vote on HB 1002", "did SB 5016 pass the Senate". Voice votes and committee-only votes are not recorded here. Keyless.

NameTypeReqDescription
bienniumstring–Washington biennium, e.g. "2025-26" or a year like "2026". Omit for the current biennium.
billstringyesBill number, with or without prefix: "HB 1002", "SB 5016", or bare "1002".

No output schema declared.

{"bill":"HB 1002"}
wa_rcw_section ~162

Get the FULL TEXT of a section of the Revised Code of Washington (RCW) — Washington state STATUTES — by citation. "RCW 9A.32.030" is first degree murder. Returns the statutory text and its heading. Keyless. Use for "what does RCW 46.61.502 say", "text of RCW 49.60.180", or to check a Washington statute a case relies on. For agency RULES (Washington Administrative Code, citations like "WAC 296-800-110") use wa_wac_section instead.

NameTypeReqDescription
sectionstringyesRCW citation, e.g. "9A.32.030" or "46.61.502". Title.chapter.section.

No output schema declared.

{"section":"9A.32.030"}
{"section":"46.61.502"}
wa_session_bills ~322

List Washington State legislative bills for a BIENNIUM filtered by procedural status: "introduced" (every bill filed, default), "passed_house", "passed_senate", "passed_legislature", "signed" (by the Governor), "vetoed", or "partial_veto" (the last three require agency: "House" or "Senate", the chamber of origin). Returns aggregate counts (by chamber, by type, active count) first, then a page of bare bill records (id, type, chamber, active) — call wa_bill_status on an id for its description. Reads directly from the Washington State Legislature's own bill-tracking service. Use for "how many bills passed the Legislature in 2025-26", "what did the Governor sign from the House in 2025-26". Keyless.

NameTypeReqDescription
agencystring–Chamber of origin, "House" or "Senate" — required for status signed/vetoed/partial_veto.
bienniumstring–Washington biennium, e.g. "2025-26" or a year like "2026". Omit for the current biennium.
limitnumber–Max records to return, default 15, max 50.
offsetnumber–Pagination offset into the full result set, default 0.
statusstring–One of: introduced (default), passed_house, passed_senate, passed_legislature, signed, vetoed, partial_veto.

No output schema declared.

{"biennium":"2025-26","limit":5,"status":"passed_legislature"}
{"agency":"House","biennium":"2025-26","limit":3,"status":"signed"}
wa_wac_archived_section ~224

Get the text of a Washington Administrative Code (WAC) section AS IT STOOD at the end of a PAST YEAR, from the Legislature's annual WAC archive. Year-end snapshots with full text for 2019 onward (e.g. "WAC 296-800-110 in 2020"); 2004–2018 are PDF-only and the tool returns the chapter PDF link for 2016–2018 and the archive directory for earlier years rather than text. Returns the archived text, caption and the history line as printed that year, so you can diff it against wa_wac_section (current). Keyless. Use for "what did WAC 314-55-010 say in 2021", or to check which version of a rule applied on a date.

NameTypeReqDescription
sectionstringyesWAC section citation, e.g. "296-800-110".
yearnumberyesArchive year, 2004–last year. Full text for 2019 onward; PDF-only before that.

No output schema declared.

{"section":"296-800-110","year":2020}
{"section":"314-55-010","year":2021}
wa_wac_browse ~163

Browse the structure of the Washington Administrative Code (WAC): with no cite, lists every WAC TITLE with the agency it belongs to (Title 296 = Labor and Industries, 458 = Revenue, 388 = Social and Health Services, 173 = Ecology, 246 = Health); with a title ("296") lists its CHAPTERS with captions; with a chapter ("296-800") lists its SECTIONS with captions and subheadings. Use to find which chapter covers a topic before calling wa_wac_section, or to enumerate every rule in a chapter. Keyless.

NameTypeReqDescription
citestring–Omit for all titles; a title number ("296") for its chapters; a chapter ("296-800") for its sections.

No output schema declared.

{"cite":"296-800"}
{"cite":"296"}
wa_wac_filings ~156

List the Washington State Register (WSR) rule-making FILINGS that affected a Washington Administrative Code (WAC) section or chapter — the amendment history as agency actions: WSR number, filing type (Permanent Rule, Proposal Original Notice, Emergency Rule, Expedited Rule Making, Preproposal Statement of Inquiry…), date filed, and a link to the filing text. Newest first. Use for "when was WAC 296-800-110 last amended", "is there a pending proposal to change chapter 458-20 WAC", or to trace a rule's rule-making record. Keyless.

NameTypeReqDescription
citestringyesWAC section ("296-800-110") or chapter ("296-800").

No output schema declared.

{"cite":"296-800-110"}
{"cite":"458-20"}
wa_wac_search ~229

Search the FULL TEXT of the Washington Administrative Code (WAC) by topic or keyword — "workplace safety bulletin board", "security deposit", "septic system permit", "cannabis retailer". Calls the Washington State Legislature's own full-text search index of every WAC section (it matches rule TEXT, not just captions), returns matching citations with captions, highlighted snippets and the index-wide match count. Optionally restrict to a title or chapter with cite_prefix ("296" for L&I, "458-20" for Revenue excise-tax rules). Call wa_wac_section with a citation for the full text and history. Keyless.

NameTypeReqDescription
cite_prefixstring–Optional WAC title or chapter to restrict results to, e.g. "296" or "296-800".
limitnumber–Max results to return, default 10, max 25.
querystringyesTopic or keywords, e.g. "safety bulletin board" or "landlord deposit". Plain words; the index is Elasticsearch-style (all terms, stemmed).

No output schema declared.

{"limit":5,"query":"safety bulletin board"}
wa_wac_section ~267

Get the CURRENT FULL TEXT of a section of the Washington Administrative Code (WAC) — Washington state agency RULES / regulations — by citation. "WAC 296-800-110" is L&I's safe-workplace summary; "458-20-178" is the Department of Revenue use-tax rule. Returns the rule text, its caption, the statutory-authority history (every WSR filing that amended it, with filed/effective dates) and the RCW sections the agency cited as authority. A repealed or nonexistent section is reported as found:false (the site redirects it). Keyless. Use for "what does WAC 296-800-110 say", "text of WAC 388-76-10000", or to check a Washington regulation an agency decision cites. For STATUTES (RCW) use wa_rcw_section; for past years use wa_wac_archived_section; to search by topic use wa_wac_search.

NameTypeReqDescription
sectionstringyesWAC citation, title-chapter-section, e.g. "296-800-110" or "WAC 458-20-178". Chapter and title parts may carry a letter suffix ("296-14A-100", "132C-120-010").

No output schema declared.

{"section":"296-800-110"}
{"section":"WAC 458-20-178"}
Install

How do I install the Washington Code MCP server?

Washington Code is a hosted endpoint at https://gateway.pipeworx.io/washington-code/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · gateway.pipeworx.io

# add to Claude Code
claude mcp add --transport http pipeworx-io-washington-code 'https://gateway.pipeworx.io/washington-code/mcp'
Common questions

What is the Washington Code MCP server?

Washington Code is an MCP server listed in the public MCP registry as io.github.pipeworx-io/washington-code. Washington state law: the Revised Code of Washington (RCW, statutes), the Washington… This page covers its hosted endpoint (https://gateway.pipeworx.io/washington-code/mcp).

Is the Washington Code MCP server safe to use?

Washington Code scores 78 out of 100 on VerifyMCP. 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 Washington Code MCP server expose?

Washington Code exposes 54 tools: ask_pipeworx, ask_pipeworx_beta, ask_pipeworx_grounded, search_within, deep_research, and 49 more. Their descriptions and schemas cost roughly 25,138 tokens of context every time the server is loaded.

Does the Washington Code MCP server require authentication?

Yes. Washington Code asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the Washington Code MCP server still maintained?

Washington Code is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Washington Code MCP server?

VerifyMCP ran 13 checks on Washington Code, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.