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.

io.github.jbiggs77/bizinsured

REMOTE · BIZINSURED.AI

AI-powered commercial insurance carrier recommendations for small businesses.

Available components

+1 this week 80 Trust /100

Last scanned (23 hours ago)

Scores higher than 81% of remote servers

Reachable. Last reached 4 Nov 2026.

Category Finance and Payments

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 Security74
Transport & Reachability100
Schema Quality & AI Usability56
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 1855 tokens (~371/item across 5 items; 5 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 Management97
  • Stability observed for 29 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage78
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 35% of tool parameters carry a description.Partial
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • We read all 5 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 6 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
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.

  • 4 Nov 26 0
    • Stability: pass → 0.97 functional
  • 30 Oct 26 +1
    • Stability: fail → pass ▲ security
  • 26 Oct 26 +2

    No change was recorded against any check on this day. Stability & Change Management went from 80 to 90.

  • 14 Oct 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 70 to 80.

  • 30 Sept 26 0
    • Authorization: unverified → partial ▲ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “classify_business” rewrote its description, which is the text the model reads security
    • Tool “connect_with_agent” rewrote its description, which is the text the model reads security
    • Tool “explain_coverage” rewrote its description, which is the text the model reads security
    • Tool “get_carrier_recommendations” rewrote its description, which is the text the model reads security
    • Tool “suggest_coverages” rewrote its description, which is the text the model reads security
    • Schema quality: 155 → 371 ▼ functional
    • “suggest_coverages” changed the type of “employee_count”: number → integer ▼ functional
    • Tool coverage: 14% → 35% ▲ functional
    • Schema quality: fair → good functional
    • Server version: 1.0.0 → 1.1.0 functional
    • “classify_business” reworded the description of “business_description” cosmetic
    • “classify_business” reworded the description of “state” cosmetic
    • “connect_with_agent” reworded the description of “recommendation_id” cosmetic
    • “connect_with_agent” reworded the description of “user_state” cosmetic
    • “explain_coverage” reworded the description of “coverage_type” cosmetic
    • “get_carrier_recommendations” reworded the description of “business_description” cosmetic
    • “get_carrier_recommendations” reworded the description of “state” cosmetic
    • “suggest_coverages” reworded the description of “business_description” cosmetic
    • “suggest_coverages” reworded the description of “naics_code” cosmetic
    • “suggest_coverages” reworded the description of “state” cosmetic
    • “suggest_coverages” reworded the description of “vertical” cosmetic
    • “connect_with_agent” dropped the optional parameter “recommended_carriers” cosmetic
    • “connect_with_agent” dropped the optional parameter “user_zip_code” cosmetic
    • “explain_coverage” dropped the optional parameter “business_context” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “city” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “current_carrier” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “current_policy_expiration” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “prior_loss_details” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “serves_food” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “source” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “vehicle_types” cosmetic
    • “get_carrier_recommendations” dropped the optional parameter “zip_code” cosmetic
    • Tool “classify_business” changed its title: Classify a business cosmetic
    • Tool “connect_with_agent” changed its title: Request a licensed agent cosmetic
    • Tool “explain_coverage” changed its title: Explain a coverage cosmetic
    • Tool “get_carrier_recommendations” changed its title: Estimate premiums and match carriers cosmetic
    • Tool “suggest_coverages” changed its title: Suggest coverages cosmetic
  • 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
  • 26 Sept 26 0
    • Tool “connect_with_agent” rewrote its description, which is the text the model reads security
    • “connect_with_agent” reworded the description of “user_zip_code” cosmetic
    • “connect_with_agent” made “user_zip_code” optional cosmetic
  • 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 4 Nov 2026 · Probed https://bizinsured.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=bizinsured.ai CN=YE2,O=Let's Encrypt,C=US 24 Sept 2026 23 Dec 2026 ECDSA 256 ECDSA-SHA384 5b4ce9b6c80344fce711152fb00f2a618cb
SANs: *.bizinsured.ai, bizinsured.ai
CN=YE2,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 4df3b15dd6c0784c507cd37b58e6f115
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of bizinsured.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 1814, 3799 8, 8 Verified
bizinsured.ai. absent 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

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://bizinsured.ai/mcp Verified 200
http (plaintext) http://bizinsured.ai/mcp HTTPS enforced 301 https://bizinsured.ai/mcp
MCP tools · 5 exposed · ~1,133 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
classify_business ~166

Use this first when the user describes what their business does, to find its insurance classification before suggesting coverages or estimating premiums. Pass only the business activity, for example 'bakery' or 'HVAC contractor'; leave out the business name, city and other details. Returns up to five candidate NAICS, ISO general liability and NCCI workers' comp code sets with a text-similarity score (not an underwriting confidence) and needsClarification. When needsClarification is true, ask the user which activity fits instead of choosing one.

NameTypeReqDescription
business_descriptionstringyesThe business activity only, e.g. 'bakery' or 'HVAC contractor'
statestring–Two-letter code of the US state where the business operates, not the user's current location

No output schema declared.

No examples provided.

connect_with_agent ~208

Use this only when the user asks to speak with an agent, get real quotes or have their coverage reviewed. Saves a referral with the business details, and the linked estimate when you pass recommendation_id, for review by a licensed agent: the BizInsured team for Ohio businesses, or a partner agent elsewhere when one is available. Returns a bizinsured.ai link where the user can choose to submit contact details. The tool does not contact anyone or request a quote, and nothing is shared with an agent until the user submits that form. Do not ask for names, emails or phone numbers in chat. Each call creates a new referral, so call it once per request.

NameTypeReqDescription
recommendation_idstring–recommendationId from get_carrier_recommendations, when you have one
risk_profileobjectyes–
user_contact_preferencestring––
user_statestringyesTwo-letter code of the US state where the business operates, not the user's current location

No output schema declared.

No examples provided.

explain_coverage ~100

Use this when the user asks what a commercial insurance coverage is or how two coverages differ. Returns a plain-language explanation of one coverage type; call it once per coverage. It cannot tell whether a specific policy covers a specific claim.

NameTypeReqDescription
coverage_typestringyesgeneral liability = GL, workers comp = WC, business owners policy = BOP, errors and omissions = professional_liability, employment practices = EPLI, liquor = liquor_liability

No output schema declared.

No examples provided.

get_carrier_recommendations ~387

Use this when the user wants premium estimates or carrier options for BOP, GL, WC or commercial_auto and you have the confirmed classification, the business's state, annual revenue and at least one coverage. Returns carriers whose appetite data matches, market budget estimates (not quotes) with sources, assumptions and caveats, and explicit estimateIssues for missing or unsupported inputs. Workers' comp in OH, WA, ND and WY is returned separately in stateFundEstimates; the Ohio figure is an estimate from published BWC rates, not a BWC quote. Omit any value the user did not give; never infer payroll from revenue. Each call saves the inputs and results in BizInsured's records and returns a recommendationId to pass to connect_with_agent; nothing is sent to carriers or agents.

NameTypeReqDescription
annual_payrollnumber–Actual annual payroll; never infer from revenue
annual_revenuenumberyes–
building_valuenumber––
business_descriptionstring–The business activity, as confirmed with classify_business
business_property_valuenumber––
coverage_limitsobject––
deductiblesobject––
desired_coveragesarrayyes–
effective_datestring––
employee_countinteger––
experience_modifiernumber––
has_alcoholboolean––
has_deliveryboolean––
iso_gl_codestring––
naics_codestring––
payroll_by_classarray–Actual payroll split by state and workers compensation classification
prior_lossesboolean––
square_footagenumber––
statestringyesTwo-letter code of the US state where the business operates
vehicle_countinteger––
years_in_businessnumber––

No output schema declared.

No examples provided.

suggest_coverages ~272

Use this when the user asks which commercial insurance coverages their business needs. Returns coverages ranked essential, recommended or optional, each with a reason, based on the confirmed class codes and the facts the user stated. Pass naics_code and iso_gl_code from classify_business after the user confirms them, and leave out facts the user did not give. Returns no prices; use get_carrier_recommendations for estimates.

NameTypeReqDescription
business_descriptionstringyesThe business activity, as confirmed with classify_business
does_deliveryboolean––
employee_countinteger––
handles_customer_databoolean––
has_physical_locationboolean––
has_vehiclesboolean––
iso_gl_codestring–Confirmed ISO GL code. For NAICS 531110 it separates 1-4 family rentals (63010) from apartment buildings (60010).
naics_codestring–Confirmed NAICS code from classify_business
serves_alcoholboolean––
serves_foodboolean––
statestringyesTwo-letter code of the US state where the business operates, not the user's current location
verticalstring–topMatch.vertical from classify_business; derived from the class codes when omitted

No output schema declared.

No examples provided.

Install

How do I install the io.github.jbiggs77/bizinsured MCP server?

io.github.jbiggs77/bizinsured is a hosted endpoint at https://bizinsured.ai/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 · bizinsured.ai

# add to Claude Code
claude mcp add --transport http jbiggs77-bizinsured 'https://bizinsured.ai/mcp'
Common questions

What is the io.github.jbiggs77/bizinsured MCP server?

io.github.jbiggs77/bizinsured is an MCP server listed in the public MCP registry as io.github.jbiggs77/bizinsured. AI-powered commercial insurance carrier recommendations for small businesses. This page covers its hosted endpoint (https://bizinsured.ai/mcp).

Is the io.github.jbiggs77/bizinsured MCP server safe to use?

io.github.jbiggs77/bizinsured scores 80 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 io.github.jbiggs77/bizinsured MCP server expose?

io.github.jbiggs77/bizinsured exposes 5 tools: classify_business, suggest_coverages, explain_coverage, get_carrier_recommendations, connect_with_agent. Their descriptions and schemas cost roughly 1,133 tokens of context every time the server is loaded.

Does the io.github.jbiggs77/bizinsured MCP server require authentication?

No. We connected to io.github.jbiggs77/bizinsured without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the io.github.jbiggs77/bizinsured MCP server still maintained?

io.github.jbiggs77/bizinsured is still listed as active in the MCP registry. We last reached this channel on 4 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.