# AgentGraph (remote · agentgraph-new.vercel.app)

Search 42,000+ MCP servers and agents by capability over one stateless MCP endpoint.

- Trust score: 69/100 (medium)
- Change this week: +3
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-11-21

## Components

- remote · `agentgraph-new.vercel.app`: 69/100 (this document), [markdown](https://verifymcp.io/servers/naithan20-agentgraph/api-mcp.md), [page](https://verifymcp.io/servers/naithan20-agentgraph/api-mcp)

## Channel facts

- Endpoint: `https://agentgraph-new.vercel.app/api/mcp`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.1.0`

## 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 not fully verified: no authorisation is required to call this server, and 11 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe.
  - 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**: 65/100
  - AI-judged instruction clarity (good).
  - Context-footprint check failed: tool/resource definitions use about 1473 tokens (~133/item across 11 items; 11 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 37/100
  - Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 89/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 67% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 11 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 12 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

## Install

### How do I install the AgentGraph MCP server?

AgentGraph is a hosted endpoint at https://agentgraph-new.vercel.app/api/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add --transport http naithan20-agentgraph 'https://agentgraph-new.vercel.app/api/mcp'
```

### Cursor

```json
{
  "mcpServers": {
    "naithan20-agentgraph": {
      "url": "https://agentgraph-new.vercel.app/api/mcp"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "naithan20-agentgraph": {
      "type": "http",
      "url": "https://agentgraph-new.vercel.app/api/mcp"
    }
  }
}
```

### Codex

```toml
[mcp_servers.naithan20-agentgraph]
url = "https://agentgraph-new.vercel.app/api/mcp"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "naithan20-agentgraph": {
      "type": "remote",
      "url": "https://agentgraph-new.vercel.app/api/mcp",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add naithan20-agentgraph --url 'https://agentgraph-new.vercel.app/api/mcp' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  naithan20-agentgraph:
    url: "https://agentgraph-new.vercel.app/api/mcp"
```

### Netclaw

```json
{
  "McpServers": {
    "naithan20-agentgraph": {
      "Transport": "http",
      "Url": "https://agentgraph-new.vercel.app/api/mcp"
    }
  }
}
```

### Vellum

```bash
assistant mcp add naithan20-agentgraph -t streamable-http -u 'https://agentgraph-new.vercel.app/api/mcp'
```

### Other

```json
{
  "mcpServers": {
    "naithan20-agentgraph": {
      "type": "http",
      "url": "https://agentgraph-new.vercel.app/api/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.

### 2026-11-20 (score 69, +1)

No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-18 (score 68, +1)

No change was recorded against any check on this day. Stability & Change Management went from 23 to 27. That category is still filling its 30-day observation window: 7 days of observed history at the previous scan, 8 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-16 (score 67, +1)

No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-14 (score 66, +1)

No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-12 (score 65, +1)

No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

### 2026-11-11 (score 64, 0)

- [functional improvement] Stability: unverified → 0.03

### 2026-11-10 (score 64)

First indexed and scored.

## MCP tools (11)

### `search_capabilities` (~313 tokens)

Search AgentGraph's index of real MCP servers and owner-submitted agents for ones that can perform a described task. Returns ranked, evidence-based results with transparent per-component scores. Every result includes machine-readable pricing (result.invocation.pricing — { mode: "FREE" } or { mode: "FIXED", amount, amountAtomic, currency, paymentProtocol, network, platformFeeBps }); paid results currently use the x402 protocol over USDC. Price is never a ranking input — it only becomes a filter when you set maxPrice/currency/paymentProtocol/freeOnly/paidOnly below, all optional.

Input parameters:

- `capability` (string): Filter by normalized capability category, e.g. "database".
- `currency` (string): Only FIXED results in this currency, e.g. "USDC" — excludes FREE results.
- `freeOnly` (boolean): Only FREE results (includes every Tool, which has no pricing concept).
- `limit` (integer)
- `maxPrice` (string): Decimal string in display units, e.g. "0.05" — includes FREE results and FIXED results priced at or below this amount.
- `paidOnly` (boolean): Only FIXED-priced results.
- `paymentProtocol` (string): Only FIXED results using this payment protocol, e.g. "X402" — excludes FREE results.
- `protocol` (string): Filter by protocol, e.g. "mcp".
- `task` (string, required): Free-text description of the task to accomplish.

### `find_tools` (~73 tokens)

List and filter indexed tools without a ranked task query — useful for browsing by capability, provider, or protocol.

Input parameters:

- `capability` (string)
- `limit` (integer)
- `protocol` (string)
- `provider` (string)
- `q` (string): Free-text substring match on name/description.

### `get_tool` (~28 tokens)

Get the full public profile of a single indexed tool by id.

Input parameters:

- `id` (string, required)

### `search_agents` (~118 tokens)

List and filter owner-submitted agents without a ranked task query — useful for browsing by capability, protocol, owner, or verification status. Use search_capabilities for a ranked task-driven search across both tools and agents.

Input parameters:

- `capability` (string)
- `limit` (integer)
- `owner` (string): Substring match on owner name.
- `protocol` (string): One of: a2a, mcp, other.
- `q` (string): Free-text substring match on name/description.
- `verified` (boolean)

### `get_agent` (~36 tokens)

Get the full public profile of a single owner-submitted agent by id, including its reported interaction summary.

Input parameters:

- `id` (string, required)

### `get_agent_invocation` (~298 tokens)

Get the machine-readable invocation contract for an owner-submitted agent: whether it's directly callable, which protocol (MCP, A2A, HTTP_JSON), the endpoint, auth requirements, input/output schemas where declared, and pricing (result.pricing — { mode: "FREE" } or { mode: "FIXED", amount, amountAtomic, currency, paymentProtocol, network, platformFeeBps, paymentRecipient }). An Agent may expose more than one contract for different capabilities (e.g. one for image comparison, a separate one for free-text idea evaluation) — pass `capability` to get the one that actually serves it; without it, this returns the Agent's primary/default contract plus a `multipleContracts`/`invocationsUrl` pointer if there's more than one. Use get_agent_invocations to list every contract at once. For a FIXED/X402 contract, use get_payment_requirement to obtain a standards-compliant x402 v2 payment requirement before invoking. Owner-submitted and unverified unless verificationStatus says otherwise — AgentGraph does not call this endpoint itself; the caller invokes the provider directly and reports the outcome via the interactions API.

Input parameters:

- `capability` (string): Optional normalized capability name — returns the contract mapped to it, if any, instead of the Agent's primary/default contract.
- `id` (string, required): Agent id (or agentgraph:agent:<id> — the plain id also works).

### `get_agent_invocations` (~87 tokens)

List every invocation contract an owner-submitted agent has declared — the unambiguous, capability-scoped view for an Agent that exposes more than one separately-callable surface. Each entry lists exactly which capabilities it serves. AgentGraph does not call any of these itself.

Input parameters:

- `id` (string, required): Agent id (or agentgraph:agent:<id> — the plain id also works).

### `get_payment_requirement` (~222 tokens)

V0.6 — for a FIXED/X402 invocation contract, returns a real, standards-compliant x402 v2 PaymentRequired object (x402Version, resource, accepts[]) built fresh from that contract's current price/network/recipient. For a FREE contract, returns { pricing: { mode: "FREE" } } and nothing else — there is no payment requirement to construct. AgentGraph is not the resource being paid for: `resource.url` in the response is the agent's own invocation endpoint, and payment settles directly to the agent's own configured wallet — AgentGraph never custodies funds. After paying, present the resulting payment authorization to POST /api/agents/{id}/invocations/{label}/payment for verification/settlement, then invoke the agent's endpoint directly, exactly as for a free contract.

Input parameters:

- `id` (string, required): Agent id (or agentgraph:agent:<id> — the plain id also works).
- `label` (string): Which invocation contract, if the Agent has more than one (default: "default").

### `get_demand` (~105 tokens)

V0.4 demand intelligence: deterministic aggregates over real search telemetry — top intent concepts, top matched capabilities (rank<=10), and how many recent searches had zero currently-callable Agent in their top 10. No LLM/clustering — every result reports its sample size and window. Mirrors GET /api/demand.

Input parameters:

- `days` (integer): Lookback window in days (default 30).
- `limit` (integer): Max capabilities to return (default 20).

### `get_opportunities` (~135 tokens)

V0.4 opportunity feed: capabilities with real recent demand (>=minSampleSize top-10 matches) sorted by weakest current callable-Agent supply first. Every entry is a real, sample-sized aggregate — see excludedForSampleSize for how many low-sample capabilities were dropped rather than shown with a misleading count. Mirrors GET /api/opportunities.

Input parameters:

- `days` (integer): Lookback window in days (default 30).
- `limit` (integer): Max opportunities to return (default 20).
- `minSampleSize` (integer): Minimum top-10 match count for a capability to be included (default 3).

### `get_capability` (~32 tokens)

Get a single capability record by id, including which tool or agent exposes it.

Input parameters:

- `id` (string, required)

## Diagnostics

Captured diagnostic sections: TLS, DNSSEC, Authorisation, Transports. The full working is on the page: https://verifymcp.io/servers/naithan20-agentgraph/api-mcp#diagnostics

## Score history

- 2026-11-21: 69
- 2026-11-20: 69
- 2026-11-19: 68
- 2026-11-18: 68
- 2026-11-17: 67
- 2026-11-16: 67
- 2026-11-15: 66
- 2026-11-14: 66
- 2026-11-13: 65
- 2026-11-12: 65
- 2026-11-11: 64
- 2026-11-10: 64

## Common questions

### What is the AgentGraph MCP server?

AgentGraph is an MCP server listed in the public MCP registry as io.github.naithan20/agentgraph. Search 42,000+ MCP servers and agents by capability over one stateless MCP endpoint. This page covers its hosted endpoint (https://agentgraph-new.vercel.app/api/mcp).

### Is the AgentGraph MCP server safe to use?

AgentGraph scores 69 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 AgentGraph MCP server expose?

AgentGraph exposes 11 tools: search_capabilities, find_tools, get_tool, search_agents, get_agent, and 6 more. Their descriptions and schemas cost roughly 1,447 tokens of context every time the server is loaded.

### Does the AgentGraph MCP server require authentication?

No. We connected to AgentGraph without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

### Is the AgentGraph MCP server still maintained?

AgentGraph 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 AgentGraph MCP server?

VerifyMCP ran 12 checks on AgentGraph, covering TLS certificate, HTTPS, HSTS header, DNSSEC and 8 more. One item could not be completed, a gap on our side rather than a finding about AgentGraph: Authorization. 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://agentgraph-new.vercel.app/api/mcp
- Website: https://agentgraph-new.vercel.app/
- Changelog RSS feed: https://verifymcp.io/servers/naithan20-agentgraph/api-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/naithan20-agentgraph/api-mcp/changelog.json
- Trust report (JSON): https://verifymcp.io/servers/naithan20-agentgraph/api-mcp.json
- HTML version of this page: https://verifymcp.io/servers/naithan20-agentgraph/api-mcp
