Bezal — Local Business Intelligence for AI Agents
REMOTE · APP.BEZAL.AI
Search 7,000+ local service businesses across America by category, location, or keyword.
Available components
Last scanned (14 hours ago)
Scores higher than 84% of remote servers
Reachable. Last reached 21 Nov 2026.
Category CRM and Sales
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 Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability80
- AI-judged instruction clarity (excellent).Pass
- Context-footprint check failed: tool/resource definitions use about 1030 tokens (~114/item across 9 items; 9 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 Management68
- Stability check failed: schema churn in the 30 days we've observed: 4 tool removals, 0 breaking changes, 0 auth/transport breaks, 0 additions. See how to fix → Fail
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 9 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 9 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
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 →
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 0
- Tool “search_businesses” rewrote its description, which is the text the model reads security
- Schema quality: pass → fail ▼ functional
- “search_businesses” added an optional parameter “county” cosmetic
- “search_by_city” reworded the description of “city” cosmetic
- 11 Nov 26 0
- Tool “search_businesses” rewrote its description, which is the text the model reads security
- 10 Nov 26 0
- Tool “compare_businesses” rewrote its description, which is the text the model reads security
- Tool “get_business” rewrote its description, which is the text the model reads security
- Tool “search_businesses” rewrote its description, which is the text the model reads security
- Tool “search_by_city” rewrote its description, which is the text the model reads security
- Tool “search_by_service” rewrote its description, which is the text the model reads security
- 7 Nov 26 0
- “search_businesses” reworded the description of “query” cosmetic
1 cosmetic change on this day. Switch on “Show cosmetic changes” to see it.
- 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
- 29 Oct 26 +6
- Stability: pass → fail ▼ security
- A breaking change shipped without a version bump: still 1.2.0 ▼ security
- Tool “get_provider_details” was removed ▼ security
- Tool “request_service” was removed ▼ security
- Tool “search_providers” was removed ▼ security
- Tool “submit_quote_request” was removed ▼ security
- Authorization: unverified → partial ▲ security
- Tool “compare_businesses” rewrote its description, which is the text the model reads security
- Tool “get_business” rewrote its description, which is the text the model reads security
- Tool “search_businesses” rewrote its description, which is the text the model reads security
- Tool “search_by_city” rewrote its description, which is the text the model reads security
- Tool “search_by_service” rewrote its description, which is the text the model reads security
- Schema quality: 87 → 99 ▼ functional
- Tool coverage: 72% → 100% ▲ functional
- Schema quality: good → excellent functional
- Destructive annotations: 0 → pass functional
- Tool “check_business_availability” changed its title: Check business availability cosmetic
- Tool “compare_businesses” changed its title: Compare businesses cosmetic
- Tool “get_business” changed its title: Get a business profile cosmetic
- Tool “get_reviews” changed its title: Get reviews cosmetic
- Tool “get_service_catalog” changed its title: Get service catalog cosmetic
- Tool “list_categories” changed its title: List categories cosmetic
- Tool “search_businesses” changed its title: Search businesses cosmetic
- Tool “search_by_city” changed its title: Search by city cosmetic
- Tool “search_by_service” changed its title: Search by service 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
- 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
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://app.bezal.ai/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=app.bezal.ai | CN=YR1,O=Let's Encrypt,C=US | 21 Oct 2026 | 19 Jan 2027 | RSA 2048 | SHA256-RSA | 676e045b29fac81985b06465eac8d988556 |
| SANs: app.bezal.ai | ||||||
| CN=YR1,O=Let's Encrypt,C=US (CA) | CN=Root YR,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | RSA 2048 | SHA256-RSA | a20253f15f2691c05dc1ce13b9bcca4e |
| CN=Root YR,O=ISRG,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | RSA 4096 | SHA256-RSA | f24b6d17f9d9ad7cb1c9fea78782699f |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of app.bezal.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| bezal.ai. | 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 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://app.bezal.ai/api/mcp | Verified | 200 | |
| http (plaintext) | http://app.bezal.ai/api/mcp | HTTPS enforced | 308 | https://app.bezal.ai/api/mcp |
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 →
check_business_availability Check business availability ~89
Check whether a business is open on a date, based on its posted opening hours. Hours are shared only for providers on a paid Bezal plan, and other listings come back with open set to "unknown". It doesn't know about bookings, so confirm a time with the business.
| Name | Type | Req | Description |
|---|---|---|---|
| business_id | string | yes | Business UUID |
| date | string | yes | ISO date (YYYY-MM-DD) |
No output schema declared.
No examples provided.
compare_businesses Compare businesses ~133
Compare up to 5 businesses side by side: the public profile fields plus services, BezalRank and whether the profile is claimed. Every business includes name, category, city, state, rating, review count, tier and quote_request_url (its public Bezal profile, where a person can send a request). Phone, website, address, hours, photos, coordinates and a booking link (when the provider saved one) are included only for providers on a paid Bezal plan, and the description only for providers on a higher paid plan.
| Name | Type | Req | Description |
|---|---|---|---|
| business_ids | array | yes | Array of business UUIDs to compare |
No output schema declared.
No examples provided.
get_business Get a business profile ~125
Get the public Bezal profile for one business by UUID. Every business includes name, category, city, state, rating, review count, tier and quote_request_url (its public Bezal profile, where a person can send a request). Phone, website, address, hours, photos, coordinates and a booking link (when the provider saved one) are included only for providers on a paid Bezal plan, and the description only for providers on a higher paid plan. For services, use get_service_catalog.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | The UUID of the business to look up |
No output schema declared.
No examples provided.
get_reviews Get reviews ~66
Get reviews for a specific business: Bezal reviews (rating, text, verified flag, date and the reviewer as first name and last initial) plus the Google rating and review count.
| Name | Type | Req | Description |
|---|---|---|---|
| business_id | string | yes | Business UUID |
| limit | number | – | Max reviews to return |
No output schema declared.
No examples provided.
get_service_catalog Get service catalog ~42
Get services and pricing for a specific business. Falls back to the list of service names if no priced catalog exists.
| Name | Type | Req | Description |
|---|---|---|---|
| business_id | string | yes | Business UUID |
No output schema declared.
No examples provided.
list_categories List categories ~17
List all available business categories in the directory.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
search_businesses Search businesses ~247
Search local business profiles on Bezal by name, category, or location. Everyday words work too, so "tech help" finds IT Services and "plumber" finds Plumbing. A Connecticut county searches the towns in it. Every business includes name, category, city, state, rating, review count, tier and quote_request_url (its public Bezal profile, where a person can send a request). Phone, website, address, hours, photos, coordinates and a booking link (when the provider saved one) are included only for providers on a paid Bezal plan, and the description only for providers on a higher paid plan.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Category keyword (e.g. "plumbing", "hr consulting") |
| city | string | – | City name |
| county | string | – | County name, e.g. "Litchfield". Connecticut counties only so far. Ignored when city names a town. |
| limit | number | – | Number of results to return (1-20) |
| query | string | – | Free-text search across business name and category (3 characters or more) |
| state | string | – | Two-letter state code or full state name |
No output schema declared.
No examples provided.
search_by_city Search by city ~158
Search for businesses in a specific city, optionally filtered by category. Every business includes name, category, city, state, rating, review count, tier and quote_request_url (its public Bezal profile, where a person can send a request). Phone, website, address, hours, photos, coordinates and a booking link (when the provider saved one) are included only for providers on a paid Bezal plan, and the description only for providers on a higher paid plan.
| Name | Type | Req | Description |
|---|---|---|---|
| category | string | – | Category keyword filter |
| city | string | yes | City name, or a Connecticut county as in "Litchfield County" |
| limit | number | – | Max results |
| state | string | – | Two-letter state code or full name |
No output schema declared.
No examples provided.
search_by_service Search by service ~153
Find businesses that list a specific service, when you know the exact service rather than the category (for example "Drain cleaning" rather than "plumbing"). Every business includes name, category, city, state, rating, review count, tier and quote_request_url (its public Bezal profile, where a person can send a request). Phone, website, address, hours, photos, coordinates and a booking link (when the provider saved one) are included only for providers on a paid Bezal plan, and the description only for providers on a higher paid plan.
| Name | Type | Req | Description |
|---|---|---|---|
| location | string | – | Optional city or state to filter by |
| service_type | string | yes | Exact service offered (matched against the services list) |
No output schema declared.
No examples provided.
How do I install the Bezal — Local Business Intelligence for AI Agents MCP server?
Bezal — Local Business Intelligence for AI Agents is a hosted endpoint at https://app.bezal.ai/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 · app.bezal.ai
claude mcp add --transport http ai-bezal-local-commerce 'https://app.bezal.ai/api/mcp'
What is the Bezal — Local Business Intelligence for AI Agents MCP server?
Bezal — Local Business Intelligence for AI Agents is an MCP server listed in the public MCP registry as ai.bezal/local-commerce. Search 7,000+ local service businesses across America by category, location, or keyword. This page covers its hosted endpoint (https://app.bezal.ai/api/mcp).
Is the Bezal — Local Business Intelligence for AI Agents MCP server safe to use?
Bezal — Local Business Intelligence for AI Agents scores 84 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 Bezal — Local Business Intelligence for AI Agents MCP server expose?
Bezal — Local Business Intelligence for AI Agents exposes 9 tools: search_businesses, get_business, list_categories, search_by_service, get_reviews, and 4 more. Their descriptions and schemas cost roughly 1,030 tokens of context every time the server is loaded.
Does the Bezal — Local Business Intelligence for AI Agents MCP server require authentication?
No. We connected to Bezal — Local Business Intelligence for AI Agents without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Bezal — Local Business Intelligence for AI Agents MCP server still maintained?
Bezal — Local Business Intelligence for AI Agents 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 Bezal — Local Business Intelligence for AI Agents MCP server?
VerifyMCP ran 13 checks on Bezal — Local Business Intelligence for AI Agents, 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.