# Objective Trust

> Objective Trust is a freemium MCP server for developer tools. Remote MCP endpoint that ranks MCP servers by health checks and your own outcomes. It runs as a hosted remote server, so there is nothing to install locally.

- **Kind:** MCP server
- **Pricing:** Freemium
- **Starting price:** $9 a month
- **Platforms:** API, Web
- **Website:** https://agentshare.dev/docs
- **Repository:** https://github.com/anhmtk/agent-price-api
- **MCP Registry name:** io.github.anhmtk/objective-trust
- **Categories:** developer tools, AI models and LLM tooling
- **Listing updated:** 2026-11-15

## About

Objective Trust is one of the MCP tools run by AgentShare, an agent-first API that bills per request with HTTP 402 (x402) or with an API key. It is served as a remote Streamable HTTP endpoint and aims to tell an agent which MCP endpoints are worth paying for before it spends anything.

AgentShare separates two kinds of evidence. Its own periodic probes check whether a registered server answers an initialize call and a tools/list call about once every 24 hours. Caller outcomes are recorded per API key, and Objective Trust combines them with the probe results. AgentShare says payment does not buy rank: featured placement only changes sort order.

The docs describe a registry review that approves listings that are honest and inspectable, and reject scams or tools that ask for seed phrases or private keys. Schema changes found on later tools/list calls do not feed the trust score.

## Features

- **Health-based ranking:** Orders MCP endpoints by observed health from AgentShare's periodic probes.
- **Caller outcome evidence:** Takes in outcomes recorded per API key alongside AgentShare's own checks.
- **Dual-auth access:** Calls are paid with an API key or per request through x402 USDC payments.
- **Evidence over reputation:** Rank is based on observed checks, not brand or popularity, and sponsorship is labelled.
- **Remote endpoint:** Connects over Streamable HTTP with no local install.

## Good for

- Pick between several MCP servers that do the same job
- Check whether a server is responding before an agent pays for it
- Feed an agent's own success and failure results back into server selection
- Screen registry entries before wiring them into an agent

## Install

### Claude Code (Terminal)

```sh
claude mcp add --transport http objective-trust https://agentshare.dev/mcp/objective-trust
```

### Claude Desktop (Settings → Connectors → Add custom connector)

```sh
https://agentshare.dev/mcp/objective-trust
```

### Cursor (~/.cursor/mcp.json)

```json
{
  "mcpServers": {
    "objective-trust": {
      "url": "https://agentshare.dev/mcp/objective-trust"
    }
  }
}
```

### VS Code (.vscode/mcp.json)

```json
{
  "servers": {
    "objective-trust": {
      "type": "http",
      "url": "https://agentshare.dev/mcp/objective-trust"
    }
  }
}
```

### Windsurf (~/.codeium/windsurf/mcp_config.json)

```json
{
  "mcpServers": {
    "objective-trust": {
      "serverUrl": "https://agentshare.dev/mcp/objective-trust"
    }
  }
}
```

### Other clients (your client's MCP settings (most use this shape))

```json
{
  "mcpServers": {
    "objective-trust": {
      "type": "http",
      "url": "https://agentshare.dev/mcp/objective-trust"
    }
  }
}
```

## FAQ

### How does Objective Trust decide what to rank?

It combines AgentShare's own health probes with outcomes the caller has recorded under their API key; the docs say the two kinds of evidence are kept separate.

### How is it paid for?

AgentShare's tools accept an X-API-Key or per-request x402 payment in USDC. Live amounts come from the PAYMENT-REQUIRED header, not a fixed price list.

### Can a provider pay for a better trust score?

The docs say no: payment does not buy health, review or rank, and featured placement only changes sort order.

### How often are listed servers checked?

About once every 24 hours with an initialize call, then tools/list if it responds.

### Is Objective Trust free?

Objective Trust has a free plan, with paid plans for more usage or features. Paid plans start at $9 a month.

### How do I add Objective Trust to Claude Code?

Run this command in your terminal: claude mcp add --transport http objective-trust https://agentshare.dev/mcp/objective-trust

### What are the best alternatives to Objective Trust?

The closest alternatives to Objective Trust are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

## Alternatives

- [REA](https://ai-powered.com/mcp/rea): REA is an open-source MCP server for developer tools.
- [Codebase Memory](https://ai-powered.com/mcp/codebase-memory): Codebase Memory is an open-source MCP server for knowledge and memory.
- [GitHub](https://ai-powered.com/mcp/github-2): GitHub is an open-source MCP server for developer tools.
- [Serena MCP: the IDE for your agent](https://ai-powered.com/mcp/serena-mcp-the-ide-for-your-agent): Serena MCP: the IDE for your agent is an open-source MCP server for developer tools.
- [XERJ](https://ai-powered.com/mcp/xerj): XERJ is an open-source MCP server for knowledge and memory.
- [Ouroboros](https://ai-powered.com/mcp/ouroboros): Ouroboros is an open-source MCP server for developer tools.
- [Claude Code Ultimate Guide](https://ai-powered.com/mcp/claude-code-ultimate-guide): Claude Code Ultimate Guide is an open-source MCP server for ai models and llm tooling.
- [Concord MCP](https://ai-powered.com/mcp/concord-mcp): Concord MCP is a freemium MCP server for developer tools.

---
Source: https://ai-powered.com/mcp/objective-trust
