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.

AgentValCon — Agent Value Gateway

REMOTE · AGENTCONCIERGE.BIZ

Find AI agents and MCP servers for a task, ranked by recorded checks. Check one before you call.

+2 this week 68 Trust /100

Last scanned (22 hours ago)

Scores higher than 52% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Search and Retrieval

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 Usability61
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 4519 tokens (~196/item across 23 items; 23 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 Management33
  • Stability check failed: schema churn in the 12 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 10 additions. See how to fix → Fail
Tool Coverage95
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 83% of tool parameters carry a description.Partial
  • Structured output schemas are declared (70% 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 23 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
  • An AI judge read all 24 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.

  • 21 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “necklace_website_trust_brief” rewrote its description, which is the text the model reads security
    • Tool coverage: 92% → 83% ▼ functional
    • Schema quality: 3722 → 4519 ▼ functional
    • Tool coverage: 84% → 70% ▼ functional
    • New tool “necklace_airport_arrival_weather_brief” functional
    • New tool “necklace_daily_fortune_brief” functional
    • New tool “necklace_personality_fortune_brief” functional
    • New tool “necklace_quakes_near_address” functional
  • 20 Nov 26 0
    • Tool “necklace_website_trust_brief” rewrote its description, which is the text the model reads security
    • Schema quality: 3365 → 3722 ▼ functional
    • Tool coverage: 89% → 84% ▼ functional
    • New tool “necklace_quakes_near_airport” functional
  • 19 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool coverage: 100% → 89% ▼ functional
    • Schema quality: 2973 → 3365 ▼ functional
    • Server version: 1.1.0 → 1.2.0 functional
    • New tool “necklace_details” functional
    • New tool “necklace_website_trust_brief” functional
  • 18 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “adapt_rest” rewrote its description, which is the text the model reads security
    • Tool “call” rewrote its description, which is the text the model reads security
    • Tool “chat” rewrote its description, which is the text the model reads security
    • Tool “check_agent” rewrote its description, which is the text the model reads security
    • Tool “credit” rewrote its description, which is the text the model reads security
    • Tool “find_agents” rewrote its description, which is the text the model reads security
    • Tool “hello” rewrote its description, which is the text the model reads security
    • Tool “report” rewrote its description, which is the text the model reads security
    • Tool “search” rewrote its description, which is the text the model reads security
    • Tool “search_workflows” rewrote its description, which is the text the model reads security
    • Tool “verify_contact” rewrote its description, which is the text the model reads security
    • Tool “whats_new” rewrote its description, which is the text the model reads security
    • Tool “workflow_details” rewrote its description, which is the text the model reads security
    • Schema quality: excellent → good functional
  • 17 Nov 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “best_for_role” rewrote its description, which is the text the model reads security
    • Tool “check_agent” rewrote its description, which is the text the model reads security
    • Tool “find_agents” rewrote its description, which is the text the model reads security
    • Tool “search” rewrote its description, which is the text the model reads security
    • Server version: 1.0.0 → 1.1.0 functional
    • “best_for_role” dropped the optional parameter “ads” cosmetic
    • “find_agents” dropped the optional parameter “ads” cosmetic
    • “search” dropped the optional parameter “ads” cosmetic
    • Tool “adapt_rest” changed its title: Call a REST API from its OpenAPI document cosmetic
    • Tool “call” changed its title: Run a listed tool here cosmetic
    • Tool “chat” changed its title: Ask about a task cosmetic
    • Tool “check_agent” changed its title: Check an agent before calling cosmetic
    • Tool “credit” changed its title: Read workspace credits cosmetic
    • Tool “find_agents” changed its title: Find agents to connect cosmetic
    • Tool “hello” changed its title: Start a session cosmetic
    • Tool “report” changed its title: Report a call outcome cosmetic
    • Tool “search” changed its title: Browse agents for a task cosmetic
    • Tool “search_workflows” changed its title: Browse published workflows cosmetic
    • Tool “verify_contact” changed its title: Confirm a contact code cosmetic
    • Tool “whats_new” changed its title: Re-check a saved task cosmetic
    • Tool “workflow_details” changed its title: Read one workflow cosmetic
  • 15 Nov 26 +1
    • Tool “best_for_role” rewrote its description, which is the text the model reads security
    • Tool “find_agents” rewrote its description, which is the text the model reads security
    • Tool “search” rewrote its description, which is the text the model reads security
    • Tool “verify_agent” rewrote its description, which is the text the model reads security
    • Schema quality: good → excellent functional
    • “best_for_role” added an optional parameter “ads” cosmetic
    • “find_agents” added an optional parameter “ads” cosmetic
    • “search” added an optional parameter “ads” cosmetic
  • 14 Nov 26 −1
    • Stability: 0.13 → fail ▼ security
    • A breaking change shipped without a version bump: still 1.0.0 ▼ security
    • Tool “subscribe” was removed ▼ security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “adapt_rest” rewrote its description, which is the text the model reads security
    • Tool “call” rewrote its description, which is the text the model reads security
    • Tool “chat” rewrote its description, which is the text the model reads security
    • Tool “find_agents” rewrote its description, which is the text the model reads security
    • Tool “search” rewrote its description, which is the text the model reads security
    • Tool “call” no longer declares itself destructive security
    • Schema quality: excellent → good functional
    • Destructive annotations: 100 → pass functional
    • New tool “best_for_role” functional
    • New tool “verify_agent” functional
  • 13 Nov 26 0
    • Tool “find_agents” rewrote its description, which is the text the model reads security
    • Tool “search” rewrote its description, which is the text the model reads security
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://agentconcierge.biz/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=agentconcierge.biz CN=YE1,O=Let's Encrypt,C=US 15 Oct 2026 13 Jan 2027 ECDSA 256 ECDSA-SHA384 619bf158a265cfa6a20b37f5482829b23c0
SANs: *.agentconcierge.biz, agentconcierge.biz
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
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 agentconcierge.biz. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
biz. DS published 13117 13 Verified
agentconcierge.biz. 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=31536000; includeSubDomains
content-security-policy default-src 'none'; img-src 'self' data:; script-src 'none'; script-src-attr 'none'; object-src 'none'; style-src 'unsafe-inline'; connect-src 'self'; frame-ancestors 'none'; base-uri 'none'; form-action 'none'
x-content-type-options nosniff
x-frame-options DENY
referrer-policy no-referrer
permissions-policy camera=(), microphone=(), geolocation=()

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://agentconcierge.biz/mcp Verified 200
http (plaintext) http://agentconcierge.biz/mcp HTTPS enforced 308 https://agentconcierge.biz/mcp
MCP tools · 23 exposed · ~4,123 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
adapt_rest ~233

Turn a public OpenAPI document into tools you can call, or call one of its endpoints (action list_tools only reads the document; action call sends the request). A call sends the HTTP method the document declares, including POST, PUT or DELETE, to that public API without credentials, so it can change data there. Use when the API you need has an OpenAPI document but no MCP server. Example arguments: {"spec_url": "https://api.example.org/openapi.json", "action": "list_tools"}

NameTypeReqDescription
actionstring–Action: 'list_tools' to discover executable tools, 'call' to invoke an endpoint.
argumentsobject–Arguments for the tool invocation.
base_urlstring–Optional override for API base URL.
specobject–Inline OpenAPI JSON specification object.
spec_urlstring–URL of the OpenAPI/Swagger JSON specification.
toolstring–Tool name to execute when action='call'.
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

best_for_role ~88

Read-only: the verified pearls (agents that passed our tests for this role) and the necklaces that run this job, if any is offered, from our latest tests. Roles look like weather.forecast.v1. Ads: at most one offer labelled "Sponsored" may follow the results in a separate `sponsored` field; it never changes the results.

NameTypeReqDescription
rolestringyes–
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
sponsoredarray–At most one offer labelled Sponsored, after and apart from the results. Each item carries `sponsored: true` and a `disclosure` object: advertising does not affect ranking, selection or test results.
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

call ~300

Run a read-only tool of a recommended agent through our gateway and get its answer in this session, after checking its current schema. Only tools classified read-only are relayed; destructive tools and tools that need the provider's own credentials are refused. A paid listing runs only with a payment proof you supply. Do not retry an uncertain outcome automatically. Use when you have chosen a listing and want this gateway to run one of its admitted tools. Example arguments: {"resource_id": 133020, "tool": "get_country_profile", "arguments": {"country_code": "US"}}

NameTypeReqDescription
account_idstring–Optional credit account ID for paid tools (defaults to your visitor ID)
argumentsobject–Key-value arguments to pass to the tool
idempotency_keystring–Stable caller key for supported ticketed delivery while its execution record is retained. Reuse with identical input; uncertain execution stays paused for review.
paymentobject–Optional payment details (tx_hash, signature, headers) for paid endpoints
resource_idintegeryesThe resource_id of the agent, MCP server, or API to call
taskstring–The task query (optional; used to find immediate alternatives if execution fails)
toolstringyesThe specific tool name to execute
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

chat ~141

Find an agent by describing your task in plain English and narrowing it over several turns ('only free ones', 'details 1', 'more', 'what's new', 'stop'). Keeps the conversation for your visitor token; replies are in English. Use when a conversation helps: refine a previous list ("only free ones"), ask for "details 2", or "more". Example arguments: {"message": "find a weather forecast API"}

NameTypeReqDescription
messagestringyesPlain-English request or follow-up, at most 2000 characters.
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

check_agent ~163

See an agent's recorded status, success rate and latency before you call it, with its grade, evidence sources and up to three alternatives (read-only, for an endpoint or agent-card URL). The URL is only looked up, never called. Use it before each call, also for agents we recommended earlier: status changes between checks. Use before each call to an agent, including one we recommended earlier, or when you already have an agent URL. Example arguments: {"url": "https://agent.example.org/.well-known/agent-card.json"}

NameTypeReqDescription
urlstringyesThe agent's endpoint or agent-card URL (public http or https).
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

credit ~123

Read your virtual credit balance (visitor token required). Top-ups and subscriptions are being prepared; this tool only reads the current balance. Use when you need your own credit balance before a paid call. Example arguments: {"action": "balance", "visitor_token": "vt_..."}

NameTypeReqDescription
account_idstring–Your own visitor account ID (defaults to the authenticated visitor ID)
actionstringyesAction: balance to check your credits.
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

find_agents ~344

Get up to three recently verified agents for your task, with what you need to call each one (endpoint, verification evidence, calling details). Stateless and read-only; no conversation is saved. price_status is free, paid (price_usdc per call in micro-USDC) or paid_or_unknown (the provider states a price or none is known; price_usdc is null). A listing our gateway can run has connection_available (same as gateway_ready) and run_here: pass its arguments to this server's call tool to run it in this session; mcp_config is a settings entry for an MCP host. Each result shows when the agent was last checked; before a later call, run check_agent on its endpoint, and if a call fails, call report with ok false for alternatives. Use when you want to connect to one of them now or run it here with call. Example arguments: {"task": "extract text from a PDF", "kind": "mcp"} Ads: at most one offer labelled "Sponsored" may follow the results in a separate `sponsored` field; it never changes the results.

NameTypeReqDescription
authstring–Compatibility field; authentication preference does not affect ranking.
categorystring–Compatibility field; task relevance is derived from the task text.
kindstring–Explicit recommendation protocol filter; Any searches A2A then MCP, excluding x402. Defaults to A2A first, then MCP; x402 requires an explicit choice.
taskstringyesWhat you need done
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
sponsoredarray–At most one offer labelled Sponsored, after and apart from the results. Each item carries `sponsored: true` and a `disclosure` object: advertising does not affect ranking, selection or test results.
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

hello ~87

Get a visitor token so later calls remember you (optional). Greets you and asks what you need. Use when you want this service to remember you across calls. Example arguments: {"name": "travel-planner-agent"}

NameTypeReqDescription
namestring–Your agent name
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

necklace_airport_arrival_weather_brief ~214

Necklace (a workflow of tested agents: 2 verified pearls): Check the destination airport, its current local time, and the ground-level daily forecast in one response. One call instead of finding, calling and merging several agents yourself. The location step runs on our own agent; an external alternative is being added. Scope: Ground-level destination weather for passenger planning. Forecasts can change. Consult your airline for flight status and official aviation weather services for operational decisions. Example arguments: {"code":"SFO"}. Free to run for now. If that changes, we will say so on its page first. Your input is sent to the agents listed in necklace_details; if one fails, the same input may go to a listed alternate. No credentials or payments are sent. Results come from third-party agents; review them before you rely on them.

NameTypeReqDescription
codestringyes–
detailstring–full (default) or brief: the same facts, values and links in fewer tokens.

No output schema declared.

No examples provided.

necklace_daily_fortune_brief ~235

Necklace (a workflow of tested agents: 4 agents under verification): Today's fortune from your birth date (Korean saju and Western sun sign). For entertainment; not advice. One call instead of finding, calling and merging several agents yourself. The calendar, western, saju, synthesis steps run on our own agent; an external alternative is being added. Example arguments: {"birth_date":"1990-05-15","calendar":"solar"}. Free to run for now. If that changes, we will say so on its page first. Your input is sent to the agents listed in necklace_details; if one fails, the same input may go to a listed alternate. No credentials or payments are sent. Results come from third-party agents; review them before you rely on them.

NameTypeReqDescription
birth_datestringyes–
birth_hourinteger––
calendarstring––
detailstring–full (default) or brief: the same facts, values and links in fewer tokens.
is_leap_monthboolean––
todaystring––

No output schema declared.

No examples provided.

necklace_details ~45

Read one necklace before you run it: its pearls (agents) and alternates per step, recent test results, completion and cost. Read-only.

NameTypeReqDescription
slugstringyes–

No output schema declared.

No examples provided.

necklace_personality_fortune_brief ~249

Necklace (a workflow of tested agents: 5 agents under verification): Today's fortune from your birth date (Korean saju and Western sun sign), read through your four-letter personality type (16 types). For entertainment; not advice. One call instead of finding, calling and merging several agents yourself. The profile, calendar, western, saju, synthesis steps run on our own agent; an external alternative is being added. Example arguments: {"age":30,"type":"INTJ"}. Free to run for now. If that changes, we will say so on its page first. Your input is sent to the agents listed in necklace_details; if one fails, the same input may go to a listed alternate. No credentials or payments are sent. Results come from third-party agents; review them before you rely on them.

NameTypeReqDescription
ageintegeryesage in full years (Korean 'man' age)
detailstring–full (default) or brief: the same facts, values and links in fewer tokens.
todaystring––
typestringyesa four-letter personality type code such as INTJ or ENFP

No output schema declared.

No examples provided.

necklace_quakes_near_address ~210

Necklace (a workflow of tested agents: 3 verified pearls): Where an address or landmark is, as coordinates, and the earthquakes of magnitude 4.5 or more within 1,000 km of it in the last 7 days (USGS data), each with magnitude, time, place and distance, and the local time there now. One call instead of finding, calling and merging several agents yourself. Example arguments: {"address":"Tokyo Tower, Minato, Tokyo, Japan"}. Free to run for now. If that changes, we will say so on its page first. Your input is sent to the agents listed in necklace_details; if one fails, the same input may go to a listed alternate. No credentials or payments are sent. Results come from third-party agents; review them before you rely on them.

NameTypeReqDescription
addressstringyes–
detailstring–full (default) or brief: the same facts, values and links in fewer tokens.

No output schema declared.

No examples provided.

necklace_quakes_near_airport ~227

Necklace (a workflow of tested agents: 2 verified pearls and 1 agent under verification): Where an airport is (from its IATA or ICAO code) and the M4.5+ earthquakes within 1,000 km of it in the last 7 days (USGS data), each with magnitude, time, place and distance, and the local time there now. One call instead of finding, calling and merging several agents yourself. The location step runs on our own agent; an external alternative is being added. Example arguments: {"code":"LAX"}. Free to run for now. If that changes, we will say so on its page first. Your input is sent to the agents listed in necklace_details; if one fails, the same input may go to a listed alternate. No credentials or payments are sent. Results come from third-party agents; review them before you rely on them.

NameTypeReqDescription
codestringyes–
detailstring–full (default) or brief: the same facts, values and links in fewer tokens.

No output schema declared.

No examples provided.

necklace_website_trust_brief ~321

Necklace (a workflow of tested agents: 2 verified pearls and 1 agent under verification): A trust brief on one domain: when it was registered, its SPF and DMARC mail records, its TLS certificate, and (optional) whether AI crawlers may read it. What each step uses (as of 2026-11-18, version 2): registration date and registrar come from RDAP (a verified third-party agent); mail authentication reads the domain's published SPF and DMARC records from DNS (a verified third-party agent); the TLS step reads the certificate the site presents (our own agent); the AI crawler check is optional. Which fallback each step has is listed under the agents below. DKIM is not checked: a DKIM record can only be looked up with the sender's selector, which a domain does not publish. One call instead of finding, calling and merging several agents yourself. The tls step runs on our own agent; an external alternative is being added. Example arguments: {"domain":"python.org"}. Free to run for now. If that changes, we will say so on its page first. Your input is sent to the agents listed in necklace_details; if one fails, the same input may go to a listed alternate. No credentials or payments are sent. Results come from third-party agents; review them before you rely on them.

NameTypeReqDescription
detailstring–full (default) or brief: the same facts, values and links in fewer tokens.
domainstringyes–

No output schema declared.

No examples provided.

report ~219

Tell us whether a call worked; on a failure, get up to three currently verified alternatives and eligible published workflows (no retry is executed). Retain the selected protocol and reject known shared failure domains. Use after a call to record the outcome and, on failure, get verified alternatives. Example arguments: {"resource_id": 133020, "ok": false, "error_type": "timeout"}

NameTypeReqDescription
errorstring–Optional error message or reason on failure
error_typestring–Optional structured failure category. This report never authorizes a retry.
okbooleanyesWhether the tool call succeeded (true) or failed (false)
protocolstring–Optional explicit recovery scope; otherwise retain the prior selection.
resource_idintegeryesThe resource_id of the agent/tool that was executed
taskstring–The task query (optional; defaults to your last searched task)
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

run_workflow ~133

Run one published workflow after reviewing it with workflow_details. Pass the definition_hash you reviewed; a changed workflow is refused. Ask for a task (params.task) to get a task id at once and follow it with tasks/get, tasks/result and tasks/cancel. Only published templates run; paid (x402) steps never run without their own explicit choice.

NameTypeReqDescription
definition_hashstringyesdefinition_hash returned by workflow_details for the version you reviewed.
inputobject–Declared product input fields, when the workflow has them.
template_idintegeryesPublished workflow id from search_workflows.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

search ~284

Compare up to three catalog agents for a task by name, grade and last successful check. Stateless and read-only; no conversation is saved. Searches A2A first, then MCP; x402 requires an explicit choice. price_status is free, paid or paid_or_unknown (price_usdc null). Returns the same ranked list as find_agents; use find_agents when you are ready to connect. Use when you want to browse and compare candidates for one task before choosing. Example arguments: {"task": "translate a document to Spanish"} Ads: at most one offer labelled "Sponsored" may follow the results in a separate `sponsored` field; it never changes the results.

NameTypeReqDescription
authstring–Compatibility field; authentication preference does not affect ranking.
categorystring–Compatibility field; task relevance is derived from the task text.
kinteger–Compatibility field; at most three results is returned.
kindstring–Explicit recommendation protocol filter; Any searches A2A then MCP, excluding x402. Defaults to A2A first, then MCP; x402 requires an explicit choice.
taskstringyesThe specific capability needed (e.g. 'weather forecast', 'stock price', 'web search')
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
sponsoredarray–At most one offer labelled Sponsored, after and apart from the results. Each item carries `sponsored: true` and a `disclosure` object: advertising does not affect ranking, selection or test results.
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

search_workflows ~118

Find up to three ready-made multi-agent workflows (necklaces) for a purpose, by capability or common aliases. Discovery does not execute it. Use when a multi-step published workflow may already do your task. Example arguments: {"task": "technology news with supporting research"}

NameTypeReqDescription
protocolstring–Optional explicit constraint on workflow node protocols.
taskstringyesThe outcome you need, in plain language.
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

verify_agent ~93

Read-only check of one agent from our latest tests: result per role, score items out of 100, how accuracy was checked, whether it is a verified pearl, test time, response fingerprint, verified alternatives for the same role and, if one is offered, a necklace for the job. Give agent_id or url.

NameTypeReqDescription
agent_idinteger––
urlstring–Endpoint or agent-card URL.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

verify_contact ~104

This legacy contact check is closed. Use POST /api/task-updates with an explicit task scope. Closed; task updates use POST /api/task-updates with an explicit task scope. Example arguments: {"code": "123456", "visitor_token": "vt_..."}

NameTypeReqDescription
codestringyesThe six-digit code delivered to your contact.
visitor_tokenstringyesYour visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

whats_new ~92

Re-check the evidence for the last task you saved with chat, without changing it. Use chat to save a task first (valid visitor token required). Use when you saved a task through chat earlier and want its evidence re-checked. Example arguments: {"visitor_token": "vt_..."}

NameTypeReqDescription
visitor_tokenstringyesYour visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

workflow_details ~100

See a published workflow's steps and whether it is ready to run. Review inputs and use the existing authorized workflow run API to execute. Use after search_workflows to inspect one workflow's steps and readiness. Example arguments: {"template_id": 12}

NameTypeReqDescription
template_idintegeryesThe workflow id returned by search_workflows.
visitor_tokenstring–Your visitor token (vt_…) so I remember you. Omit on first contact.
NameTypeReqDescription
executionobject––
intentstring––
okboolean––
recommendationsarray––
statusstring––
textstringyes–
visitorobject|null––

No examples provided.

Install

How do I install the AgentValCon — Agent Value Gateway MCP server?

AgentValCon — Agent Value Gateway is a hosted endpoint at https://agentconcierge.biz/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 · agentconcierge.biz

# add to Claude Code
claude mcp add --transport http biz-agentconcierge-agent-concierge 'https://agentconcierge.biz/mcp'
Common questions

What is the AgentValCon — Agent Value Gateway MCP server?

AgentValCon — Agent Value Gateway is an MCP server listed in the public MCP registry as biz.agentconcierge/agent-concierge. Find AI agents and MCP servers for a task, ranked by recorded checks. Check one before you call. This page covers its hosted endpoint (https://agentconcierge.biz/mcp).

Is the AgentValCon — Agent Value Gateway MCP server safe to use?

AgentValCon — Agent Value Gateway scores 68 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 AgentValCon — Agent Value Gateway MCP server expose?

AgentValCon — Agent Value Gateway exposes 23 tools: hello, chat, search, find_agents, check_agent, and 18 more. Their descriptions and schemas cost roughly 4,123 tokens of context every time the server is loaded.

Does the AgentValCon — Agent Value Gateway MCP server require authentication?

No. We connected to AgentValCon — Agent Value Gateway without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the AgentValCon — Agent Value Gateway MCP server still maintained?

AgentValCon — Agent Value Gateway 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 AgentValCon — Agent Value Gateway MCP server?

VerifyMCP ran 13 checks on AgentValCon — Agent Value Gateway, 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.