# 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.

- Trust score: 68/100 (medium)
- Change this week: +2
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `agentconcierge.biz`: 68/100 (this document), [markdown](https://verifymcp.io/servers/biz-agentconcierge-agent-concierge/agentconcierge.md), [page](https://verifymcp.io/servers/biz-agentconcierge-agent-concierge/agentconcierge)

## Channel facts

- Endpoint: `https://agentconcierge.biz/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `1.1.0`

## Trust breakdown

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. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-11-21.

- **Endpoint Security**: 63/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (adapt_rest).
  - HTTPS is enforced; there's no plaintext access path.
  - The HSTS (Strict-Transport-Security) header is present.
  - DNSSEC check failed: this domain isn't protected by DNSSEC.
- **Transport & Reachability**: 100/100
  - Verified streamable-http transport via a live MCP handshake.
- **Schema Quality & AI Usability**: 61/100
  - AI-judged instruction clarity (good).
  - 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.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 33/100
  - Stability check failed: schema churn in the 12 days we've observed: 1 tool removals, 0 breaking changes, 0 auth/transport breaks, 10 additions.
- **Tool Coverage**: 95/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 83% of tool parameters carry a description.
  - Structured output schemas are declared (70% of tools); any adoption earns full credit.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 23 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 24 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.

## 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.

### Claude

```bash
claude mcp add --transport http biz-agentconcierge-agent-concierge 'https://agentconcierge.biz/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "biz-agentconcierge-agent-concierge": {
      "url": "https://agentconcierge.biz/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "biz-agentconcierge-agent-concierge": {
      "type": "http",
      "url": "https://agentconcierge.biz/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.biz-agentconcierge-agent-concierge]
url = "https://agentconcierge.biz/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "biz-agentconcierge-agent-concierge": {
      "type": "remote",
      "url": "https://agentconcierge.biz/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add biz-agentconcierge-agent-concierge --url 'https://agentconcierge.biz/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  biz-agentconcierge-agent-concierge:
    url: "https://agentconcierge.biz/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "biz-agentconcierge-agent-concierge": {
      "Transport": "http",
      "Url": "https://agentconcierge.biz/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add biz-agentconcierge-agent-concierge -t streamable-http -u 'https://agentconcierge.biz/mcp'
```

### Other

```json
{
  "mcpServers": {
    "biz-agentconcierge-agent-concierge": {
      "type": "http",
      "url": "https://agentconcierge.biz/mcp"
    }
  }
}
```

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-11-21 (score 68, 0)

- [security] 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
- [functional regression] Tool coverage: 92% → 83%
- [functional regression] Schema quality: 3722 → 4519
- [functional regression] 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”

### 2026-11-20 (score 68, 0)

- [security] Tool “necklace_website_trust_brief” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 3365 → 3722
- [functional regression] Tool coverage: 89% → 84%
- [functional] New tool “necklace_quakes_near_airport”

### 2026-11-19 (score 68, 0)

- [security] The server rewrote its instructions, which are the text every model session reads
- [functional regression] Tool coverage: 100% → 89%
- [functional regression] 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”

### 2026-11-18 (score 68, 0)

- [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 “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
- [functional] Schema quality: excellent → good

### 2026-11-17 (score 68, +1)

- [security] 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
- [functional] Server version: 1.0.0 → 1.1.0
- [cosmetic] “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

### 2026-11-15 (score 67, +1)

- [security] 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
- [functional] Schema quality: good → excellent
- [cosmetic] “best_for_role” added an optional parameter “ads”
- [cosmetic] “find_agents” added an optional parameter “ads”
- [cosmetic] “search” added an optional parameter “ads”

### 2026-11-14 (score 66, −1)

- [security regression] Stability: 0.13 → fail
- [security regression] A breaking change shipped without a version bump: still 1.0.0
- [security regression] 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
- [functional] Schema quality: excellent → good
- [functional] Destructive annotations: 100 → pass
- [functional] New tool “best_for_role”
- [functional] New tool “verify_agent”

### 2026-11-13 (score 67, 0)

- [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

## MCP tools (23)

### `hello` (~87 tokens)

Start a session

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"}

Input parameters:

- `name` (string): Your agent name
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `chat` (~141 tokens)

Ask about a task

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"}

Input parameters:

- `message` (string, required): Plain-English request or follow-up, at most 2000 characters.
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `search` (~284 tokens)

Browse agents for a task

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.

Input parameters:

- `auth` (string): Compatibility field; authentication preference does not affect ranking.
- `category` (string): Compatibility field; task relevance is derived from the task text.
- `k` (integer): Compatibility field; at most three results is returned.
- `kind` (string): Explicit recommendation protocol filter; Any searches A2A then MCP, excluding x402. Defaults to A2A first, then MCP; x402 requires an explicit choice.
- `task` (string, required): The specific capability needed (e.g. 'weather forecast', 'stock price', 'web search')
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `sponsored` (array): 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.
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `find_agents` (~344 tokens)

Find agents to connect

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.

Input parameters:

- `auth` (string): Compatibility field; authentication preference does not affect ranking.
- `category` (string): Compatibility field; task relevance is derived from the task text.
- `kind` (string): Explicit recommendation protocol filter; Any searches A2A then MCP, excluding x402. Defaults to A2A first, then MCP; x402 requires an explicit choice.
- `task` (string, required): What you need done
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `sponsored` (array): 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.
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `check_agent` (~163 tokens)

Check an agent before calling

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"}

Input parameters:

- `url` (string, required): The agent's endpoint or agent-card URL (public http or https).
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `whats_new` (~92 tokens)

Re-check a saved task

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_..."}

Input parameters:

- `visitor_token` (string, required): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `verify_contact` (~104 tokens)

Confirm a contact code

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_..."}

Input parameters:

- `code` (string, required): The six-digit code delivered to your contact.
- `visitor_token` (string, required): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `call` (~300 tokens)

Run a listed tool here

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"}}

Input parameters:

- `account_id` (string): Optional credit account ID for paid tools (defaults to your visitor ID)
- `arguments` (object): Key-value arguments to pass to the tool
- `idempotency_key` (string): Stable caller key for supported ticketed delivery while its execution record is retained. Reuse with identical input; uncertain execution stays paused for review.
- `payment` (object): Optional payment details (tx_hash, signature, headers) for paid endpoints
- `resource_id` (integer, required): The resource_id of the agent, MCP server, or API to call
- `task` (string): The task query (optional; used to find immediate alternatives if execution fails)
- `tool` (string, required): The specific tool name to execute
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `report` (~219 tokens)

Report a call outcome

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"}

Input parameters:

- `error` (string): Optional error message or reason on failure
- `error_type` (string): Optional structured failure category. This report never authorizes a retry.
- `ok` (boolean, required): Whether the tool call succeeded (true) or failed (false)
- `protocol` (string): Optional explicit recovery scope; otherwise retain the prior selection.
- `resource_id` (integer, required): The resource_id of the agent/tool that was executed
- `task` (string): The task query (optional; defaults to your last searched task)
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `credit` (~123 tokens)

Read workspace credits

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_..."}

Input parameters:

- `account_id` (string): Your own visitor account ID (defaults to the authenticated visitor ID)
- `action` (string, required): Action: balance to check your credits.
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `adapt_rest` (~233 tokens)

Call a REST API from its OpenAPI document

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"}

Input parameters:

- `action` (string): Action: 'list_tools' to discover executable tools, 'call' to invoke an endpoint.
- `arguments` (object): Arguments for the tool invocation.
- `base_url` (string): Optional override for API base URL.
- `spec` (object): Inline OpenAPI JSON specification object.
- `spec_url` (string): URL of the OpenAPI/Swagger JSON specification.
- `tool` (string): Tool name to execute when action='call'.
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `search_workflows` (~118 tokens)

Browse published workflows

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"}

Input parameters:

- `protocol` (string): Optional explicit constraint on workflow node protocols.
- `task` (string, required): The outcome you need, in plain language.
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `workflow_details` (~100 tokens)

Read one workflow

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}

Input parameters:

- `template_id` (integer, required): The workflow id returned by search_workflows.
- `visitor_token` (string): Your visitor token (vt_…) so I remember you. Omit on first contact.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `verify_agent` (~93 tokens)

Check an agent before calling it

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.

Input parameters:

- `agent_id` (integer)
- `url` (string): Endpoint or agent-card URL.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `best_for_role` (~88 tokens)

Verified pearls for a role

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.

Input parameters:

- `role` (string, required)

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `sponsored` (array): 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.
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `run_workflow` (~133 tokens)

Run a published workflow

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.

Input parameters:

- `definition_hash` (string, required): definition_hash returned by workflow_details for the version you reviewed.
- `input` (object): Declared product input fields, when the workflow has them.
- `template_id` (integer, required): Published workflow id from search_workflows.

Output parameters:

- `execution` (object)
- `intent` (string)
- `ok` (boolean)
- `recommendations` (array)
- `status` (string)
- `text` (string)
- `visitor` (object|null)

### `necklace_airport_arrival_weather_brief` (~214 tokens)

Airport Arrival Weather Brief

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.

Input parameters:

- `code` (string, required)
- `detail` (string): full (default) or brief: the same facts, values and links in fewer tokens.

### `necklace_daily_fortune_brief` (~235 tokens)

Daily fortune

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.

Input parameters:

- `birth_date` (string, required)
- `birth_hour` (integer)
- `calendar` (string)
- `detail` (string): full (default) or brief: the same facts, values and links in fewer tokens.
- `is_leap_month` (boolean)
- `today` (string)

### `necklace_personality_fortune_brief` (~249 tokens)

Fortune by personality type

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.

Input parameters:

- `age` (integer, required): age in full years (Korean 'man' age)
- `detail` (string): full (default) or brief: the same facts, values and links in fewer tokens.
- `today` (string)
- `type` (string, required): a four-letter personality type code such as INTJ or ENFP

### `necklace_quakes_near_address` (~210 tokens)

Earthquakes near an address

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.

Input parameters:

- `address` (string, required)
- `detail` (string): full (default) or brief: the same facts, values and links in fewer tokens.

### `necklace_quakes_near_airport` (~227 tokens)

Earthquakes near an airport

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.

Input parameters:

- `code` (string, required)
- `detail` (string): full (default) or brief: the same facts, values and links in fewer tokens.

### `necklace_website_trust_brief` (~321 tokens)

Website trust brief

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.

Input parameters:

- `detail` (string): full (default) or brief: the same facts, values and links in fewer tokens.
- `domain` (string, required)

### `necklace_details` (~45 tokens)

Necklace details

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

Input parameters:

- `slug` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/biz-agentconcierge-agent-concierge/agentconcierge#diagnostics

## Score history

- 2026-11-21: 68
- 2026-11-20: 68
- 2026-11-19: 68
- 2026-11-18: 68
- 2026-11-17: 68
- 2026-11-16: 67
- 2026-11-15: 67
- 2026-11-14: 66
- 2026-11-13: 67
- 2026-11-12: 67
- 2026-11-11: 66
- 2026-11-10: 66
- 2026-11-09: 65

## 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.

## Links

- Remote endpoint: https://agentconcierge.biz/mcp
- Website: https://agentconcierge.biz/connect
- Changelog RSS feed: https://verifymcp.io/servers/biz-agentconcierge-agent-concierge/agentconcierge.xml
- Changelog JSON feed: https://verifymcp.io/servers/biz-agentconcierge-agent-concierge/agentconcierge/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/biz-agentconcierge-agent-concierge/agentconcierge.json
- HTML version of this page: https://verifymcp.io/servers/biz-agentconcierge-agent-concierge/agentconcierge
