# AgentResolver (remote · agentresolver.vercel.app)

Open-world capability procurement and verified provider routing for autonomous agents.

- Trust score: 73/100 (medium)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-09-20

## Components

- remote · `agentresolver.vercel.app`: 73/100 (this document), [markdown](https://verifymcp.io/servers/waxsway-agentresolver/mcp-control.md), [page](https://verifymcp.io/servers/waxsway-agentresolver/mcp-control)

## Channel facts

- Endpoint: `https://agentresolver.vercel.app/mcp/control`
- Transports: `streamable-http`
- Auth: `none`
- Version: `0.2.1`

## 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 2026-09-20.

- **Endpoint Security**: 80/100
  - The endpoint's TLS certificate is valid, in date, and uses a strong key.
  - No authorisation is required to call this server. Every tool declares its destructiveHint and none is destructive, so open access doesn't expose one.
  - 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**: 71/100
  - AI-judged instruction clarity (excellent).
  - Context-footprint check failed: tool/resource definitions use about 457 tokens (~228/item across 2 items; 2 tools + 0 resources), over budget; trim descriptions and params.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 3/100
  - Stability observed for 1 of 30 days with no destabilising changes; credit accrues until the full window elapses.
- **Tool Coverage**: 100/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 100% 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 2 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 3 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 AgentResolver MCP server?

AgentResolver is a hosted endpoint at https://agentresolver.vercel.app/mcp/control, 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 waxsway-agentresolver 'https://agentresolver.vercel.app/mcp/control'
```

### Cursor

```json
{
  "mcpServers": {
    "waxsway-agentresolver": {
      "url": "https://agentresolver.vercel.app/mcp/control"
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "waxsway-agentresolver": {
      "type": "http",
      "url": "https://agentresolver.vercel.app/mcp/control"
    }
  }
}
```

### Codex

```toml
[mcp_servers.waxsway-agentresolver]
url = "https://agentresolver.vercel.app/mcp/control"
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "waxsway-agentresolver": {
      "type": "remote",
      "url": "https://agentresolver.vercel.app/mcp/control",
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add waxsway-agentresolver --url 'https://agentresolver.vercel.app/mcp/control' --transport streamable-http
```

### Hermes

```yaml
mcp_servers:
  waxsway-agentresolver:
    url: "https://agentresolver.vercel.app/mcp/control"
```

### Netclaw

```json
{
  "McpServers": {
    "waxsway-agentresolver": {
      "Transport": "http",
      "Url": "https://agentresolver.vercel.app/mcp/control"
    }
  }
}
```

### Vellum

```bash
assistant mcp add waxsway-agentresolver -t streamable-http -u 'https://agentresolver.vercel.app/mcp/control'
```

### Other

```json
{
  "mcpServers": {
    "waxsway-agentresolver": {
      "type": "http",
      "url": "https://agentresolver.vercel.app/mcp/control"
    }
  }
}
```

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.

### 2026-09-20 (score 73, −1)

- [security] The server rewrote its instructions, which are the text every model session reads
- [security] Tool “resolve” rewrote its description, which is the text the model reads
- [security] Tool “procure” rewrote its description, which is the text the model reads
- [functional regression] Schema quality: 172 → 228
- [functional improvement] Stability: unverified → 0.03

### 2026-09-19 (score 74)

First indexed and scored.

## MCP tools (2)

### `procure` (~203 tokens)

Procure a compatible capability

CALL THIS when the agent's installed tools do not clearly satisfy the current task. Free open-world procurement across external APIs, MCP servers, x402/L402/MPP services, and registered providers. It enforces explicit constraints and fails closed: unproven compatibility is not selected. If no candidate can be proven, the response may include an optional $0.02 Verified Resolve action that live-checks supported unknowns; use it only with independent host spend authorization. Never authorizes spend.

Input parameters:

- `constraints` (object): Hard procurement constraints. Missing evidence is surfaced as unknown rather than assumed compatible.
- `goal` (string, required): Plain-language description of the external capability the agent needs.
- `limit` (integer): Maximum number of ranked candidates to return. Defaults to 5.
- `providerOrigins` (array): Optional provider HTTPS origins already known to the caller. AgentResolver checks only their fixed well-known provider manifest and matching live x402 routes; no arbitrary target is proxied.

### `resolve` (~114 tokens)

Resolve a missing capability

Exploratory discovery only. Use this when the caller is browsing possible capabilities and does not yet need a trustworthy execution choice. For an actual task that the agent's installed tools cannot satisfy, prefer procure so compatibility fails closed and unresolved evidence can escalate to optional paid verification.

Input parameters:

- `goal` (string, required): Plain-language description of the missing capability.
- `limit` (integer): Maximum results per discovery source. Defaults to 3.
- `url` (string): Optional public URL related to the task when discovery should consider a concrete endpoint or resource.

## Diagnostics

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

## Score history

- 2026-09-20: 73
- 2026-09-19: 74

## Common questions

### What is the AgentResolver MCP server?

AgentResolver is an MCP server listed in the public MCP registry as io.github.waxsway/agentresolver. Open-world capability procurement and verified provider routing for autonomous agents. This page covers its hosted endpoint (https://agentresolver.vercel.app/mcp/control).

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

AgentResolver scores 73 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 AgentResolver MCP server expose?

AgentResolver exposes 2 tools: procure, resolve. Their descriptions and schemas cost roughly 317 tokens of context every time the server is loaded.

### Does the AgentResolver MCP server require authentication?

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

### Is the AgentResolver MCP server still maintained?

AgentResolver is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

## Links

- Remote endpoint: https://agentresolver.vercel.app/mcp/control
- Repository: https://github.com/waxsway/agentresolver
- Changelog RSS feed: https://verifymcp.io/servers/waxsway-agentresolver/mcp-control.xml
- Changelog JSON feed: https://verifymcp.io/servers/waxsway-agentresolver/mcp-control.json
- HTML version of this page: https://verifymcp.io/servers/waxsway-agentresolver/mcp-control