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.

STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch

REMOTE · STEADYWRK.APP

Keyless storefront readiness probe linking a Store Guard audit, plus dispatch estimates and quotes.

Available components

0 this week 79 Trust /100

Last scanned (21 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category CRM and Sales

Recent critical change

Authorization (5 Sept 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 Security63
Transport & Reachability100
Schema Quality & AI Usability75
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1873 tokens (~170/item across 11 items; 9 tools + 2 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 Management100
  • No destabilizing schema changes in the last 30 days.Pass
Tool Coverage84
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 44% of tool parameters carry a description.Partial
  • Structured output schemas are declared (100% 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
  • We read all 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
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.

  • 9 Nov 26 0
    • Stability: 0.97 → pass security
  • 8 Nov 26 0
    • Stability: pass → 0.97 functional
  • 6 Nov 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 18 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “agentic.readiness_probe” rewrote its description, which is the text the model reads security
    • Tool “dispatch.order” rewrote its description, which is the text the model reads security
    • Tool “dispatch.quote” rewrote its description, which is the text the model reads security
    • Schema quality: 191 → 170 ▲ functional
    • Tool coverage: 20% → 44% ▲ functional
    • Tool coverage: 20% → 29% ▲ functional
    • Schema quality: 191 → 159 ▲ functional
    • The server now declares the “prompts” capability functional
    • The server now declares the “resources” capability functional
    • First check of Schema quality: 100 functional
    • New prompt “audit_storefront” functional
    • New prompt “price_a_job” functional
    • New resource “quickstart” functional
    • New resource “trades” functional
    • Server version: 0.2.1 → 0.3.0 functional
    • Server version: 0.1.1 → 0.2.1 functional
    • New tool “acp.validate” functional
    • New tool “ucp.validate” functional
    • New tool “dispatch.order_status” functional
    • “dispatch.order” added an optional parameter “test_mode” cosmetic
    • “dispatch.quote” added an optional parameter “test_mode” cosmetic
    • “dispatch.estimate” reworded the description of “trade” cosmetic
    • “dispatch.order” reworded the description of “trade” cosmetic
    • “dispatch.quote” reworded the description of “trade” cosmetic
  • 17 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “dispatch.quote” rewrote its description, which is the text the model reads security
    • Schema quality: 173 → 191 ▼ functional
    • “dispatch.quote” added an optional parameter “contact_email” cosmetic
    • “dispatch.quote” added an optional parameter “company” cosmetic
    • “dispatch.quote” added an optional parameter “contact_name” cosmetic
  • 11 Oct 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “dispatch.order” rewrote its description, which is the text the model reads security
    • Tool “dispatch.quote” rewrote its description, which is the text the model reads security
    • Schema quality: 151 → 173 ▼ functional
  • 28 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → functional
  • 25 Sept 26 0
    • We updated how we score, so this day's move reflects our rubric, not a change to the server See what changed → 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 21 Nov 2026 · Probed https://steadywrk.app/api/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=steadywrk.app CN=WE1,O=Google Trust Services,C=US 11 Oct 2026 9 Jan 2027 ECDSA 256 ECDSA-SHA256 12366e0df8124a951362612bdd0535c2
SANs: steadywrk.app, motion.steadywrk.app, *.motion.steadywrk.app
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 steadywrk.app. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
app. DS published 23684 8 Verified
steadywrk.app. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy accelerometer=(), autoplay=(), bluetooth=(), camera=(), display-capture=(), encrypted-media=(), fullscreen=(self), geolocation=(), gyroscope=(), hid=(), idle-detection=(), magnetometer=(), microphone=(self), midi=(), payment=(), picture-in-picture=(), publickey-credentials-get=(self), screen-wake-lock=(), serial=(), sync-xhr=(), usb=(), xr-spatial-tracking=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://steadywrk.app/api/mcp Verified 200
http (plaintext) http://steadywrk.app/api/mcp HTTPS enforced 301 https://steadywrk.app/api/mcp
MCP tools · 9 exposed · ~1,439 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
acp.validate ~127

Free validator for a store's Agentic Commerce Protocol (ACP) discovery file at /.well-known/acp.json. Pass url to fetch a public store's file, or document to check pasted JSON. Returns a verdict, every rule result, and a fix list: each failed rule with the change that fixes it. Reads one public file, stores nothing, calls no checkout endpoint. No API key required.

NameTypeReqDescription
documentstring–The discovery document's JSON text, checked without any fetch
urlstring–Public store URL or domain, e.g. shop.example.com

Structured output declared, but exposes no named fields.

No examples provided.

agentic.readiness_probe ~154

Run a one-time readiness check on a public storefront and return a score, a grade and per-check results (UCP and ACP discovery files, product schema, robots rules, answer-engine maps). The result is a dated snapshot of public files, not an attested Store Guard grade. Input: url, a public storefront URL or domain (up to 255 characters; local, private and numeric hosts are refused). Each run may store a public snapshot record, at most one per host per UTC day, linked in the response. The response also lists Store Guard and sample-report links under `next`. Rate-limited per caller. No API key required.

NameTypeReqDescription
urlstringyesPublic storefront URL or domain

Structured output declared, but exposes no named fields.

No examples provided.

dispatch.estimate ~116

Public modeled field-service price estimate with cited BLS wage benchmarks. Returns customer hourly rates, line items, ranges and a total alongside geographic scope and source provenance. Model estimates are not observed transaction prices or binding quotes. Use dispatch.quote with an accepted credential to request a quote. No API key required.

NameTypeReqDescription
locationobjectyes–
tradestringyesTrade code: hvac, plumbing, electrical, general_maintenance, roofing, painting, carpentry or locksmith (see dispatch.index).
urgencystring––

Structured output declared, but exposes no named fields.

No examples provided.

dispatch.evals ~64

Return the public evaluation document for a selected rolling window. Consult its per-field provenance and methodology to distinguish self-reported estimates, measurements, and unavailable fields. It is not an independent audit or a service-level guarantee. No API key required.

NameTypeReqDescription
periodstring––
NameTypeReqDescription
estimatedbooleanyesFalse only when every goal-fulfillment rate is backed by fresh, sufficient production telemetry. A rate without such telemetry is null, not an estimate.
goal_fulfillmentobjectyesEach rate is a live measurement or null. Null means unavailable (see provenance.by_field), not zero.
methodologyobjectyesMetric definitions, named-period window, source-class vocabulary. Never a sample size.
operationalobjectyes–
periodstringyes–
provenanceobjectyesPer-field record of whether each figure is measured (live_telemetry), a stated target or coverage statement (canonical_estimate), or unavailable (published as null).
schema_versionstringyes–
trust_signalsobjectyes–

No examples provided.

dispatch.index ~82

Return the catalog of 8 dispatch trade verticals. Per trade: the BLS OES hourly WAGE benchmark (medianRateDollars/p25/p75 — what a technician earns, NOT a price) alongside billedHourlyRateRoutineDollars, a modeled customer hourly estimate at routine urgency. Estimates are not observed transaction prices or binding quotes. No API key required.

Input schema present but exposes no named parameters.

NameTypeReqDescription
model_assumptionsstringyes–
notestringyes–
rate_model_versionstringyes–
source_periodstringyes–
tradesarrayyes–
updated_atstringyes–
wage_vs_billedobjectyes–

No examples provided.

dispatch.order ~287

Create a field-service order and return its status URL. HTTP 201 returns a created order; HTTP 202 returns an order accepted_pending_fulfilment with fulfilled=false. Order creation requires a provisioned integration key through x-api-key. MCP also accepts that key through Authorization: Bearer; direct REST order creation requires x-api-key. A self-serve OAuth token authenticates but is not entitled to create orders: HTTP 402 payment_required (JSON-RPC -32002 over MCP). Anonymous callers receive HTTP 401 with WWW-Authenticate. To be provisioned, POST JSON to https://steadywrk.app/api/integration-key-request or use https://steadywrk.app/developers/keys and a person reviews each request. Email fallback: hello@steadywrk.app.

NameTypeReqDescription
callback_urlstring––
descriptionstringyes–
locationobjectyes–
nte_centsinteger––
reference_idstring––
test_modeboolean–true: a test booking with your STEADYWRK key (any key, including the free one). Answered whether orders are open or not, marked test: true; nothing is dispatched, matched or charged.
tradestringyesTrade code, as listed by dispatch.index (e.g. plumbing, hvac, electrical).
urgencystring––

Structured output declared, but exposes no named fields.

No examples provided.

dispatch.order_status ~146

Return the current state of a work order created by dispatch.order: status, assignment, quote and timestamps. Same key as dispatch.order (the order's status_url, served over MCP). A self-serve OAuth token cannot have created an order, so it receives HTTP 402 payment_required (JSON-RPC -32002). Anonymous callers receive HTTP 401 with WWW-Authenticate. To be provisioned, POST JSON to https://steadywrk.app/api/integration-key-request or use https://steadywrk.app/developers/keys and a person reviews each request. Email fallback: hello@steadywrk.app.

NameTypeReqDescription
order_idstringyesThe order.id returned by dispatch.order.

Structured output declared, but exposes no named fields.

No examples provided.

dispatch.quote ~336

Request a field-service quote by trade, location, and urgency. Returns availability and quote details when available. Accepts a provisioned integration key through x-api-key or, when OAuth is enabled, a scoped self-serve OAuth token through Authorization: Bearer. MCP also accepts the provisioned key through Authorization: Bearer. Request an integration key: POST JSON to https://steadywrk.app/api/integration-key-request (GET it for the fields), or use https://steadywrk.app/developers/keys and a person reviews each request. Email fallback: hello@steadywrk.app. Over MCP, without a key, add contact_email (and optionally contact_name and company) and the request is filed for a person to answer by email. Other anonymous callers receive HTTP 401 with WWW-Authenticate. Public modeled pricing is available through dispatch.estimate.

NameTypeReqDescription
companystring––
contact_emailstring–Only without a key: where a person replies with the quote. The request is filed for review.
contact_namestring––
descriptionstring––
locationobjectyes–
nte_centsinteger––
test_modeboolean–true: a test booking with your STEADYWRK key (any key, including the free one). Answered whether orders are open or not, marked test: true; nothing is dispatched, matched or charged.
tradestringyesTrade code: hvac, plumbing, electrical, general_maintenance, roofing, painting, carpentry or locksmith (see dispatch.index).
urgencystring––

Structured output declared, but exposes no named fields.

No examples provided.

ucp.validate ~127

Free validator for a store's Universal Commerce Protocol (UCP) discovery file at /.well-known/ucp. Pass url to fetch a public store's file, or document to check pasted JSON. Returns a verdict, every rule result, and a fix list: each failed rule with the change that fixes it. Reads one public file, stores nothing, calls no checkout endpoint. No API key required.

NameTypeReqDescription
documentstring–The discovery document's JSON text, checked without any fetch
urlstring–Public store URL or domain, e.g. shop.example.com

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch MCP server?

STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch is a hosted endpoint at https://steadywrk.app/api/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 · steadywrk.app

# add to Claude Code
claude mcp add --transport http app-steadywrk-mcp-dispatch 'https://steadywrk.app/api/mcp'
Common questions

What is the STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch MCP server?

STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch is an MCP server listed in the public MCP registry as app.steadywrk/mcp-dispatch. Keyless storefront readiness probe linking a Store Guard audit, plus dispatch estimates and quotes. This page covers its hosted endpoint (https://steadywrk.app/api/mcp).

Is the STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch MCP server safe to use?

STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch scores 79 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 STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch MCP server expose?

STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch exposes 9 tools: agentic.readiness_probe, dispatch.quote, dispatch.estimate, dispatch.order, dispatch.order_status, and 4 more. Their descriptions and schemas cost roughly 1,439 tokens of context every time the server is loaded.

Does the STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch MCP server require authentication?

No. We connected to STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch MCP server still maintained?

STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch 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 did VerifyMCP test on the STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch MCP server?

VerifyMCP ran 13 checks on STEADYWRK Agentic Readiness Probe, Store Guard and Dispatch, 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.