MCP servers › ai.truvon › directory
MCP server · registry snapshot 2026-11-06 · last tested 2026-11-06
directory MCP server
Registry name ai.truvon/directory
Truvon — the publisher's title
by truvon.ai · domain (the registry's namespace rule)Website ↗
Find and check local U.S. businesses: open or closed, sourced phone and hours, and how to act. — the publisher's description
Summary
ai.truvon/directory is a remote MCP server listed in the official MCP registry at version 1.0.0, under the namespace of the domain truvon.ai. On 2026-11-06 ProtocolProbe connected to it in read-only mode and read its inventory: 11 tools, 0 resources and 0 prompts.
Record checks
1 of 2 record checks met · 7 do not apply
- met: Registry entry is active and says how to run it
- not met: Source repository link opens
- not applicable: Repository is not archived
- not applicable: Code pushed to the repository in the 90 days before our check
- not applicable: Repository publishes a security policy (SECURITY.md)
- not applicable: Package names its licence with a standard (SPDX) identifier
- not applicable: The version the registry lists can be installed and is not withdrawn
- not applicable: npm package carries build provenance (attestation)
- not applicable: No known critical or high advisory in the package or its dependencies
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
From public records, not a safety rating. Each check with its reason
Operate this server? Correct a fact · README badge · Run the checks yourself
Key facts
- Runs
- remote (hosted by the publisher)
- Transport
- streamable HTTP
- Your own values
- none declared (not a guarantee)
- Sign-in
- none needed to open a session
- Tools
- 11
- Last tested
- 2026-11-06
How a client gets in
Connects without signing in
Read from the server's public metadata on 2026-11-06 (truvon.ai), in our read-only connection; no tool was called. It may have changed since. How it is read
Tool list at the three APIs
Not sent yet for this version (1.0.0).
How fresh this is
- Live-tested
- yes, a real session (not a text-only review)
- Last tested
- 2026-11-06
- Mode
- read-only (no tool calls)
- Latest version
- 1.0.0, published 2026-11-05 (registry, as of the 2026-11-06 snapshot)
- First listed version
- 2026-11-05 (earliest version still in the registry; older removed versions would be earlier)
- Registry data
- snapshot 2026-11-06
- Package and repository
- checked 2026-11-06
- Engine
- mcp-runtime-engine@0.1.0 · sdk@1.32.0
Dead or stale signals
None found in the records we hold
Looked for and not found: deprecated in the registry. Does not apply: listed version cannot be installed or is withdrawn; repository link does not open; repository archived; no push in over 365 days. Each line is a dated fact from a public record. It does not say whether the server still works, and a record can change after the date shown.
Changes since the last refresh
New in the registry: not in the list of 2026-11-05, listed on 2026-11-06 with version 1.0.0 (published 2026-11-05).
Source: the official MCP Registry list on 2026-11-05 and on 2026-11-06.
What it is
What does this server offer?
Observed inventoryNone of its 11 tools are described as changing anything. For 11 the reading was uncertain, so no mark is shown.
- find_local_businesseson 1 other server
“Start here.”
Publisher declares: read-only yes · open-world no
16 inputs, 1 required
needstringrequired“The service in a few plain words: "furnace repair", "water heater leak", "bbq catering for 12".”placestring“Where the user is, always with its state: "Town, ST" (e.g.”zipstring“The user's 5-digit ZIP code, instead of place”latnumber“The user's latitude in decimal degrees, with lon: the most exact place to measure distance from”lonnumber“The user's longitude in decimal degrees, with lat”max_milesnumber“Only businesses within this many miles of the place (businesses that serve online always pass)”max_minutesnumber“Only businesses within this many minutes of estimated driving (straight line with a road and river-crossing estimate, not a routing service), counted only wher…”actionstring“Only businesses that offer this: book, order, quote, call or message (comma means any)”completableboolean“Only businesses an agent can complete the action with itself: a Truvon door, or the business's own MCP server, API or commerce endpoint once it has claimed its…”open_atstring“Open at a specific day and time in the business's local time, e.g.”pricesboolean“Only businesses that state prices”include_closedboolean“Also list businesses likely closed or closed (left out by default; open on each result says why)”limitinteger“How many results (default 5)”detailstring“compact (default) or full records”refinesstring“The search_id of an earlier search this one narrows (one choice of an "A or B", a more specific wording, an added requirement).”modelstring“Optional: the model you run on (for example claude-sonnet-5-5 or gpt-5.5), kept with this report's provenance so what each model reports can be weighed over ti…”
- more_results
“The next page of a search, with the next_cursor the search returned; kept 24 hours.”
Publisher declares: read-only yes · idempotent no · open-world no
1 input, 1 required
cursorstringrequired“next_cursor from the last find_local_businesses or more_results response”
- get_business_record
“One business's full record by website domain: prices, offers, hours, every way to act, each fact with its source and date, and every source's value where they disagree.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
domainstringrequired“The business's website domain, or its truvon_id (biz_…) from a result; the id is exact when a domain is listed in several markets.”search_idstring“The search_id this listing came from, if any”formatstring
- check_places_results
“Check up to 10 businesses you found elsewhere (maps, web, a link) before you give your user a phone or send them somewhere: open or closed with dated evidence, the phone its sources agree on, how to …”
Publisher declares: read-only yes · open-world no
8 inputs
businessesarray“Several businesses to check at once, each with what you have; place, zip and need below apply to all”namestring“One business: its name (or use businesses)”phonestringwebsitestringaddressstring“The street address as you found it”placestring“Town, ST”zipstringneedstring“Your user's need: the next step quotes the lines of each business's own pages that answer it, and may_have_missed lists the two best businesses for it that you…”
- get_field_history
“Every value one fact (phone, hours, address, name) has held, which source said it and when.”
Publisher declares: read-only yes · open-world no
3 inputs, 1 required
businessstringrequired“The truvon_id from a result (biz_…) or the business's website domain.”fieldstring“The field, e.g.”formatstring
- report_answer
“When a business told you something its record lacks ("yes, certified kosher"), record the question and its answer in its words, with the business's truvon_id.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
7 inputs, 4 required
connectionstring“The connection code connect_truvon gave you, once your user approved its link.”modelstring“Optional: the model you run on (for example claude-sonnet-5-5 or gpt-5.5), kept with this report's provenance so what each model reports can be weighed over ti…”businessstringrequired“The truvon_id from a result (biz_…) or the business's website domain.”questionstringrequired“What you asked, in your words (up to 200 characters)”answerstringrequired“What the business said, in its words as near as you can (up to 500 characters)”channelstringrequired“How you asked it”search_idstring“The search_id that led you to the business, if any”
- report_outcomeon 43 other servers
“After you have acted for your user (booked, ordered, called, got a quote): say what happened, with the search_id and the business's truvon_id.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
15 inputs, 3 required
connectionstring“The connection code connect_truvon gave you, once your user approved its link.”modelstring“Optional: the model you run on (for example claude-sonnet-5-5 or gpt-5.5), kept with this report's provenance so what each model reports can be weighed over ti…”businessstringrequired“The truvon_id from a result (biz_…) or the business's website domain.”search_idstring“The search_id from find_local_businesses, so the outcome teaches similar future needs”actionstringrequired“What you did for your user”outcomestringrequired“confirmed: the business confirmed; pending: submitted, awaiting the business; handed_off: you gave your user the link or number and they finish it (never count…”failurestring“When failed.”sourcestring“With business_closed: the link where you saw it (a news story, its own post, a listing marked closed).”kindstring“With business_closed: closed for good, or temporarily (renovation, vacation, season)”reopensstring“With a temporary closure: the reopening date it states, YYYY-MM-DD”fieldstring“With wrong_information: which fact is wrong”correctstring“With wrong_information: the right value, as you found it”viastring“How you acted: a Truvon door, the business's own agent endpoint, a platform (a booking or ordering service), its link, its phone, its email”expected_atstring“ISO time when the outcome will be knowable: delivery ETA or appointment time”assertionstring“Platforms only: your Truvon agent assertion (identity protocol §4, a JWS binding this report to your user's pairwise sub).”
- report_missingon 1 other server
“A business that fits your user's need, that you found elsewhere (the web, a map), and Truvon does not list (check_places_results said so): send its name, its own website, phone, address and the town,…”
Publisher declares: read-only no · destructive no · idempotent yes · open-world yes
10 inputs, 1 required
connectionstring“The connection code connect_truvon gave you, once your user approved its link.”modelstring“Optional: the model you run on (for example claude-sonnet-5-5 or gpt-5.5), kept with this report's provenance so what each model reports can be weighed over ti…”namestringrequired“The business's name as you found it”websitestring“Its own website (never a directory, social or maps page); without one it is recorded but cannot be read”phonestringaddressstring“Its street address as you found it”placestring“Town, ST”zipstringneedstring“The need it fits, in the plain words you searched with”search_idstring“The search_id of the search that did not return it”
- answer_follow_up
“Days later, when the outcome is knowable: send your user's answers to the questions report_outcome gave you, by follow_up id.”
Publisher declares: read-only no · destructive no · idempotent yes · open-world no
11 inputs, 1 required
connectionstring“The connection code connect_truvon gave you, once your user approved its link.”modelstring“Optional: the model you run on (for example claude-sonnet-5-5 or gpt-5.5), kept with this report's provenance so what each model reports can be weighed over ti…”follow_upstringrequiredcompletedstringreasonstringmatchedstringdifferentarraysatisfiedintegeragainstringelsewherestring“Cancelled jobs: did your user get it done elsewhere”assertionstring“Platforms only: your Truvon agent assertion (identity protocol §4, a JWS binding this report to your user's pairwise sub).”
- get_jobon 169 other servers
“When your user returns asking about a job you arranged: its status and the business's updates, by the job id report_outcome gave you.”
Publisher declares: read-only yes · open-world no
2 inputs, 1 required
connectionstring“The connection code connect_truvon gave you, once your user approved its link.”jobstringrequired“The job_id, job_…”
- connect_truvon
“When your app has not signed in to Truvon itself: get a link for your user to open and a connection code for you.”
Publisher declares: read-only no · destructive no · idempotent no · open-world no
1 input
clientstring“Your assistant or product name, for Truvon's own records (optional; never shown to the person)”
Each quoted sentence is the first sentence of the publisher’s own description. The kind of tool and the “changes data” mark are our AI model’s reading of that description, not something we tested: two differently worded runs had to agree, otherwise no label is shown, and nobody has checked them by hand. A tool without the “changes data” mark is described as only reading, searching or calculating, or the two runs did not agree. No tool was called. Read the publisher’s full description before relying on it. “Publisher declares” lists the hints the server itself sends with the tool (MCP annotations: read-only, destructive, idempotent, open-world); they are the publisher's claims, not checked by us. Inputs are the parameters in the tool's own input schema: name, declared type, whether it is required, and the first sentence of its description. Read 2026-11-06.
How well are its tools described?
Features #4 and #5
How clearly this server's own tool descriptions say what a tool does, and how consistent its tool list is. The first part is an AI model's yes/no reading of each description; the second part is counted. We do not turn it into a grade.
Descriptions
AI reading of each description
No AI reading was available for this server's tools (the two runs did not agree, or the listing was not reviewed).
Counted from the listing
- Parameters with a description
- 82% of 77
- Tools with a description
- 100% of 11
- Typical description length
- 254 characters
The tool set
Counted from the listing
- Tools
- 11
- Size of the list
- about 4,254 tokens for an agent to load (characters ÷ 4)
- Naming
- 11 of 11 names use snake_case
AI reading: easy to mix up
No pair found.
The AI items cover 0 of 11 tools: for a tool where two differently worded runs disagreed, that item is left out. They were not checked by hand, and no tool was called. “Easy to mix up” means two tools whose names or descriptions overlap without saying how they differ; the AI found none. We do not rate whether the tool set is complete or whether side effects are spelled out, because our AI reading of those was not reliable enough.
How do I add it to my client?
Config from the registry entry
From the remote endpoint (Streamable HTTP)
We connected to this URL on 2026-11-06 (a read-only session: no tool was called).
Add to CursorAn install link in the format Cursor documents, holding the Cursor config below.
Claude Desktop or claude.ai
Settings → Connectors → Add custom connector, then paste: https://truvon.ai/mcp
Cursor · .cursor/mcp.json in a project, or ~/.cursor/mcp.json
{
"mcpServers": {
"directory": {
"url": "https://truvon.ai/mcp"
}
}
}VS Code · .vscode/mcp.json
{
"servers": {
"directory": {
"type": "http",
"url": "https://truvon.ai/mcp"
}
}
}VS Code (command line) · Bash or zsh terminal (macOS, Linux)
code --add-mcp '{"name":"directory","type":"http","url":"https://truvon.ai/mcp"}'Claude Code
claude mcp add --transport http directory https://truvon.ai/mcp
Cline · cline_mcp_settings.json (Cline CLI: ~/.cline/data/settings/; in the editor: MCP Servers → Configure → Configure MCP Servers)
{
"mcpServers": {
"directory": {
"type": "streamableHttp",
"url": "https://truvon.ai/mcp",
"disabled": false,
"autoApprove": []
}
}
}Gemini CLI · ~/.gemini/settings.json, or .gemini/settings.json in a project
{
"mcpServers": {
"directory": {
"httpUrl": "https://truvon.ai/mcp"
}
}
}OpenAI Codex · ~/.codex/config.toml, or .codex/config.toml in a trusted project
[mcp_servers.directory] url = "https://truvon.ai/mcp"
Zed · Zed settings file (command: zed: open settings file)
{
"context_servers": {
"directory": {
"url": "https://truvon.ai/mcp"
}
}
}Try it in the MCP Inspector · runs on your machine, opens in your browser · Node 22.19+
npx @modelcontextprotocol/inspector@2.11.0 --server-url https://truvon.ai/mcp --transport http
- The server runs on the operator's infrastructure; it may ask you to sign in when you first connect.
- Zed's docs we read on 2026-10-26 describe remote servers by URL and do not name the transport.
- The MCP Inspector lists the server's tools, resources and prompts; a tool you call there runs for real.
Built from the server's registry entry with each client's documented format (checked 2026-10-14; the Cursor link and the VS Code command 2026-10-19; the MCP Inspector command 2026-10-21; Cline, Gemini CLI, OpenAI Codex and Zed 2026-10-26). Values in < > are yours to fill in; this page never contains a key. Where the server needs a setting the entry does not declare, it can still fail to start.
Does the registry listing match what we found?
Feature #6The registry checks an entry when it is published (each new version), and nothing re-checks it on a schedule. A difference below is about the listing, not a judgement of the publisher.
| Registry says | We found | Result | Source · date |
|---|---|---|---|
| Remote endpoint truvon.ai/mcp | Session opened | matches | our test · 2026-11-06 |
| No credential declared as required | Opened a session without any credential | matches | our test · 2026-11-06 |
Choosing
Record checks
Public records · not a safety rating1 of 2 record checks met · 7 do not apply
- Not ranked by downloads: a remote server publishes no download figure
- Not ranked by stars: no public GitHub repository
- MetRegistry entry is active and says how to run itActive, with a package or a remote address.
- Not metSource repository link opensThe registry entry gives no repository link.What changes this check: This check opens the repository link in the registry entry. GitHub's documentation describes changing a repository's visibility in its Settings, under Danger Zone, Change visibility. GitHub: setting repository visibility
- Does not applyRepository is not archivedNo public GitHub repository to read.
- Does not applyCode pushed to the repository in the 90 days before our checkNo public GitHub repository to read.
- Does not applyRepository publishes a security policy (SECURITY.md)No public GitHub repository to read.
- Does not applyPackage names its licence with a standard (SPDX) identifierRemote server: it ships no package.
- Does not applyThe version the registry lists can be installed and is not withdrawnRemote server: it ships no package.
- Does not applynpm package carries build provenance (attestation)Remote server: it ships no package.
- Does not applyNo known critical or high advisory in the package or its dependenciesRemote server: it ships no package.
Read from public records only: the registry entry, npm/PyPI, GitHub and advisory databases, checked 2026-11-06. No tool was called. Only “met” and “not met” are counted, so the total differs between servers; a check that does not apply or that we could not run is listed, never counted against it. It is not a safety rating, and the same rules apply to every server. How each check works · Leaderboards · How we stay neutral
Common questions about ai.truvon/directory
Answered from the data aboveWho publishes ai.truvon/directory?
The registry ties the namespace ai.truvon to the domain truvon.ai; only its owner can publish under it. These are facts from the registry and GitHub, not a rating.
Does ai.truvon/directory need an API key or sign-in?
It opened a session without any credential on 2026-11-06. The registry entry declares no required credential; no declaration is not a guarantee.
Has ai.truvon/directory been security tested?
Partly. 3 of the 15 checks that apply to it were exercised. We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. ProtocolProbe publishes no security verdict for a named server.
Found this page useful?
Anonymous · no sign-inA quick, anonymous reaction — no account, no email. One per kind from your browser. The tally updates when the page is next refreshed, and it is only a rough count, never a safety rating or a measured number of people.
Compare with another server
Side by side: registry entry, our read-only session, the tools and the 18 classification fields. Same values as each page; no score.
Security testing
What did we test, and what did we leave out?
18 checks · features #1, #2
Not probed (we call no server's tools)
We connected and read what the server declares, but did not call its tools: ProtocolProbe calls no server's tools for anything it publishes. This is our choice, not a block by the server. No security score is given; a check we did not run is never counted as passed.
- Inventory: exercised
- Hidden instructions: exercised
- Real execution: not run · our policy
- Secret leak: not run · nothing to check it against
- Internal addresses: not run · our policy
- Unconfirmed changes: not run · our policy
- Bad input: not run · our policy
- Model requests: not run · nothing to check it against
- Sensitive questions: not run · nothing to check it against
- Folder boundary: not run · our policy
- Log leaks: not run · nothing to check it against
- Hidden content: not run · nothing to check it against
- Fake assistant turns: not applicable
- Token passthrough: not applicable
- Token audience: not applicable
- Sign-in redirect: not run · our policy
- Consent handling: not testable from outside
- Sign-in metadata: exercised
3 exercised12 not run (reason given)3 not applicable
Each check ends in exactly one state: exercised, not run (with the reason), or not applicable (with the reason). 3 of the 15 checks that apply to it were exercised. We do not publish security-check outcomes for named servers. These 18 checks are separate from the record checks at the top of this page, which read public records only.
- 1Inventory
tool-listReads the declared tools, resources and prompts.exercised - 2Hidden instructions
description-poisoningLooks for hidden instructions in tool descriptions.exercised - 18Sign-in metadata
oauth-url-schemeChecks the published sign-in metadata for unsafe URLs.exercised
- 3Real execution
real-executionCalls a tool and checks what really happens.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 4Secret leak
canary-leakPlants a fake secret and checks whether it leaks.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 5Internal addresses
ssrfChecks whether a tool can be steered to internal addresses.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 6Unconfirmed changes
write-without-confirmationChecks whether tools that change data act without asking.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 7Bad input
error-handlingSends bad input and watches how the server answers.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 8Model requests
samplingChecks whether the server asks the client's model to act for it.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 9Sensitive questions
elicitation-sensitive-dataChecks whether the server asks users for sensitive data.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 10Folder boundary
root-boundaryChecks whether the server reaches outside the folders it was given.This check calls the server's tools. ProtocolProbe calls no server's tools for anything it publishes; an operator can run this check on their own server with our self-test command.not run · our policy - 11Log leaks
logging-side-channelChecks whether log messages carry data they should not.This check needs at least one successful tool call to have something to check, and no tool was called.not run · nothing to check it against - 12Hidden content
audience-hidingChecks resources that hide content from the user.This check needs content the server returns, and nothing was read or called.not run · nothing to check it against - 16Sign-in redirect
open-redirectChecks the sign-in redirect for abuse.Testing the sign-in redirect means sending probes to the operator's sign-in service, which we do not do.not run · our policy - 17Consent handling
confused-deputyChecks consent handling when one service acts for another.Depends on the operator's own consent screen, which differs per server and cannot be tested from outside.not testable from outside
- 13Fake assistant turns
fake-assistant-turnChecks prompts that pose as the assistant's own words.The server exposes no prompts.not applicable - 14Token passthrough
token-passthroughChecks whether the server forwards a user's token to other services.The server opened a session without sign-in, so there is no token flow to check.not applicable - 15Token audience
token-audience-validationChecks whether tokens meant for another service are accepted.The server opened a session without sign-in, so there is no token flow to check.not applicable
Source: our own test, 2026-11-06, mcp-runtime-engine@0.1.0. Which checks count and why follows our published scoring model.
What happened during the test?
Feature #8
The steps in order, as the test record holds them.
- 0 msStarted a read-only session with the server's remote endpoint
- 2,059 msConnected after 0 redirects. No credential was sent or needed.
- Read the inventory: 11 tools, 0 resources, 0 prompts.
- 3,384 msFinished: 3 checks exercised.
Reference
How is it classified?
18 fields
One value per field, each with its source. Fields written by AI models are marked. A field with no value says why.
“Not stated” means the source did not state it; “does not apply” means it does not apply to this kind of server; “our limit” means our own lookup failed. A linked value opens the directory filtered to the same value.
Cite or correct this page
Sources and corrections
Suggested citation
ProtocolProbe. “ai.truvon/directory: MCP server record.” Data checked 2026-11-06. https://protocolprobe.com/mcp/servers/ai.truvon/directory
Figures are valid for the date shown. Our facts on this page are CC BY 4.0: reuse them with a link and the check date. Quoted text (the publisher’s descriptions, website quotes, tool names) is not ours to license.
As JSON: this record in the API · API documentation.
Badge for your README
[](https://protocolprobe.com/mcp/servers/ai.truvon/directory)
It shows this server's record-check count: facts from public records, no tool called. It is not a security rating or a pass. It links here and updates after each data reload.
Something wrong, or is this yours?
If a fact here is wrong, tell us and we will re-check it. If you operate this server, you can run our checks on it yourself with the free self-test command; we call no server’s tools ourselves for anything shown here.
Write to hello@protocolprobe.com · corrections log · methodology