Clarvia

by clarvia-project

392 downloads
Not rated
GitHub

About

AEO (Agent Engine Optimization) scanner — scores and benchmarks 12,800+ AI agent tools for discoverability, quality, and agent compatibility. 14 MCP tools for searching, scanning, comparing, and benchmarking.

Details

Author
clarvia-project
Downloads
392
Categories
Developer Tools, AI, Search, API, Other

Jump to

- AEO Score (0–100) for any AI tool, API, or MCP server.
- Four scoring dimensions with detailed breakdowns.
- Search over 15,400 indexed AI tools by keyword or score.
- Safety gate tool (clarvia_gate_check) for agent workflows.
- Batch checking and alternative finding tools.
- Personalized upgrade recommendations for tool makers.

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name Clarvia
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

Install with one command: npx -y clarvia-mcp-server. Add to any MCP client configuration (Claude Desktop, Claude Code, Cursor, Windsurf, Cline, Continue.dev) or use the remote endpoint https://clarvia-api.onrender.com/mcp/. The Node.js MCP server provides 16 tools; a Python MCP server offers 24 tools.

search_services

Search 27,886+ AI agent tools (MCP servers, APIs, CLIs) by keyword, category, or score. Use when you need to find the best tool for a specific task, compare alternatives, or check agent readiness. Returns Clarvia AEO scores (0-100) indicating how easily AI agents can discover and use each service.

scan_service

Run a full AEO audit on any URL — evaluates agent discoverability, API quality, documentation, and MCP readiness. Use when you need to score a website or API for AI agent compatibility, or when building an agent and want to verify a tool meets quality standards. Returns a Clarvia score (0-100) with detailed breakdown.

get_service_details

Get the full AEO evaluation report for a previously scanned service. Use when you need detailed scoring breakdown (documentation, API design, error handling, auth, MCP support) or want to understand why a tool scored high or low. Requires a scan_id from search_services or scan_service results.

list_categories

List all tool categories in the Clarvia directory with service counts per category. Use when you need to browse available categories before searching, discover what types of AI tools exist, or build a category-based navigation for agent tool selection.

get_stats

Get aggregate statistics for the Clarvia tool directory — total indexed services, average AEO score, score distribution, and category breakdown. Use when you need an overview of the AI tool ecosystem quality, want to benchmark a tool against the average, or report on agent-readiness trends.

register_service

Submit a new AI tool, MCP server, API, or CLI for Clarvia indexing and AEO scoring. Use when you want to register your service in the directory, get an agent-readiness evaluation, or make your tool discoverable by AI agents. The service will be queued for automated scanning.

clarvia_gate_check

Before calling any external API or MCP, use this to check if it is agent-ready. Returns AGENT_NATIVE / AGENT_FRIENDLY / AGENT_POSSIBLE / AGENT_HOSTILE with a boolean pass/fail. Call this first — if the service scores below your threshold, use clarvia_find_alternatives to get a better-rated replacement automatically.

clarvia_batch_check

Batch-check up to 10 service URLs in a single call — returns pass/fail and agent grade for each. Use when comparing multiple tool candidates side-by-side, pre-filtering a list of APIs before integration, or building an agent that selects the best tool from several options. More efficient than calling gate_check repeatedly.

clarvia_find_alternatives

Find higher-rated alternative tools in a given category, ranked by agent-readiness score. Use when a service fails the gate check and you need a replacement, when comparing options in a category (payment, AI, crypto, SaaS), or when an agent needs to fall back to a better-scored tool automatically.

clarvia_probe

Run a live accessibility probe on a service URL right now — checks HTTP reachability, response latency, OpenAPI/Swagger spec presence, MCP server-card availability, and agents.json discovery endpoint. Use when you need real-time health status (not cached scores), want to verify a service is online before calling it, or are debugging connectivity issues with an agent tool.

clarvia_submit_feedback

Report the outcome after using a tool (success / failure / partial) to contribute to Clarvia's reliability dataset. Use after every agent tool invocation to help build community-driven quality signals. Accepts optional latency and error details. Improves future agent tool selection accuracy for all users.

register_my_setup

Register your current tool setup (MCP servers, CLIs, APIs, Skills) with Clarvia to get AEO scores and category rankings for each tool. Use when you want to benchmark your agent's toolchain, track setup quality over time, or prepare for comparison and upgrade recommendations. Returns a setup_id for use with compare_my_setup and recommend_upgrades.

compare_my_setup

Compare your registered tool setup against higher-scored alternatives in each category. Shows the best available upgrades for each tool and the category average score. Use after register_my_setup to identify weak spots in your toolchain and find better-rated replacements. Requires a setup_id from register_my_setup.

clarvia_report_issue

Report a bug, request a feature, ask a question, or flag a security issue with Clarvia or any indexed tool. Use when you encounter problems with a tool's AEO score, find incorrect data, want to suggest improvements to the Clarvia platform, or discover a security vulnerability. Creates a tracked ticket that the Clarvia team will address.

clarvia_list_issues

List existing CS tickets — check status of previously reported issues, see what bugs are known, or find feature requests to upvote. Use to avoid duplicate reports or to track the status of your submitted tickets.

recommend_upgrades

Get personalized tool recommendations based on your registered setup. Suggests high-scoring tools you don't have yet — both within your existing categories and in complementary adjacent categories. Uses 'users with X also use Y' heuristics. Requires a setup_id from register_my_setup.

clarvia_top_picks

Get agent-verified top picks — only tools that scored Excellent (80+) out of 27,886+ scanned. These are the most agent-ready services in the ecosystem, curated by Clarvia's AEO scoring. Use when an agent asks 'what are the best tools?' or 'recommend verified tools'.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

{
    "mcpServers": {
        "clarvia": {
            "clarvia": {
                "command": "npx",
                "args": [
                    "-y",
                    "clarvia-mcp-server"
                ]
            }
        }
    }
}

McpServers

{
    "clarvia": {
        "command": "npx",
        "args": [
            "-y",
            "clarvia-mcp-server"
        ]
    }
}

Clarvia

The AEO (Agent Engine Optimization) Standard for AI Agent Tools

Score, discover, and validate 15,400+ AI agent tools for quality, accessibility, and agent-readiness.

npm version
npm downloads
License: MIT
MCP Tools
Python Tools
Services Indexed
API Endpoints
Website

Website · npm · API Docs · Leaderboard

</div>

---

Install (one command)

npx -y clarvia-mcp-server

Or add to any MCP client config:

{
  "mcpServers": {
    "clarvia": {
      "command": "npx",
      "args": ["-y", "clarvia-mcp-server"]
    }
  }
}

No install needed? Use the remote endpoint directly:

https://clarvia-api.onrender.com/mcp/

---

What is Clarvia?

Clarvia assigns an AEO Score (0-100) to any AI tool, API, or MCP server — measuring how easily AI agents can discover, integrate, and trust it. Think of it as "Lighthouse for AI agent tools."

4 scoring dimensions (25 points each):

| Dimension | What it measures |
|---|---|
| API Accessibility | Endpoint existence, response speed, auth documentation |
| Data Structuring | Schema definition, pricing clarity, error structure |
| Agent Compatibility | MCP server presence, robots.txt, sitemap/discovery |
| Trust Signals | Uptime, documentation quality, update frequency |

Plus an optional Onchain Bonus (+25) for web3 services.

---

For Agents

> Before calling any external tool, check if it's agent-ready.

Clarvia gives your agent a quality gate for tool selection:

Agent workflow:
  Need a payment API?
  -> search_services("payment API")
  -> clarvia_gate_check(top_result)
  -> PASS? Use it. FAIL? clarvia_find_alternatives("payment")
  -> After use: clarvia_submit_feedback(result)

Agent Grades:
- AGENT_NATIVE (80+) — Built for agents, full MCP/OpenAPI support
- AGENT_FRIENDLY (60-79) — Good API, minor gaps
- AGENT_POSSIBLE (40-59) — Usable with effort
- AGENT_HOSTILE (0-39) — Avoid for autonomous use

---

For Tool Makers

> See your tool the way AI agents see it.

- Your AEO score — how agent-ready your tool is today
- Specific gaps — missing OpenAPI spec? No MCP server? Poor error messages?
- Category ranking — how you compare to alternatives
- Actionable fixes — each dimension tells you exactly what to improve

---

Quick Start by Framework

<details>
<summary><strong>Claude Desktop</strong></summary>

Add to ~/Library/Application Support/Claude/claude_desktop_config.json:

{
  "mcpServers": {
    "clarvia": {
      "command": "npx",
      "args": ["-y", "clarvia-mcp-server"]
    }
  }
}
</details>

<details>
<summary><strong>Claude Code</strong></summary>

claude mcp add clarvia -- npx -y clarvia-mcp-server
</details>

<details>
<summary><strong>Cursor</strong></summary>

Add to .cursor/mcp.json:

{
  "mcpServers": {
    "clarvia": {
      "command": "npx",
      "args": ["-y", "clarvia-mcp-server"]
    }
  }
}
</details>

<details>
<summary><strong>Windsurf</strong></summary>

Add to .windsurf/mcp.json:

{
  "mcpServers": {
    "clarvia": {
      "command": "npx",
      "args": ["-y", "clarvia-mcp-server"]
    }
  }
}
</details>

<details>
<summary><strong>Cline</strong></summary>

Add to .cline/mcp.json or VS Code settings:

{
  "mcpServers": {
    "clarvia": {
      "command": "npx",
      "args": ["-y", "clarvia-mcp-server"]
    }
  }
}
</details>

<details>
<summary><strong>Continue.dev</strong></summary>

Add to ~/.continue/config.json:

{
  "experimental": {
    "modelContextProtocolServers": [
      {
        "transport": {
          "type": "stdio",
          "command": "npx",
          "args": ["-y", "clarvia-mcp-server"]
        }
      }
    ]
  }
}
</details>

<details>
<summary><strong>Remote Endpoint (any MCP client)</strong></summary>

https://clarvia-api.onrender.com/mcp/

No local installation required. Works with any MCP client supporting Streamable HTTP transport.
</details>

See examples/ for ready-to-copy config files.

---

MCP Tools — Node.js Server (16 tools)

Discovery & Search

| Tool | Description |
|------|-------------|
| search_services | Search 15,400+ indexed AI tools by keyword, category, or minimum AEO score |
| list_categories | List all tool categories with service counts |
| get_stats | Platform-wide statistics — total services, score distributions |

Scanning & Evaluation

| Tool | Description |
|------|-------------|
| scan_service | Full AEO audit on any URL — agent discoverability, API quality, docs, MCP readiness |
| get_service_details | Detailed scoring breakdown for a scanned service |
| register_service | Submit a new service for indexing and scoring |

Agent Safety & Gating

| Tool | Description |
|------|-------------|
| clarvia_gate_check | Pass/fail safety check — agent grade with boolean result |
| clarvia_batch_check | Batch-check up to 10 URLs in one call |
| clarvia_find_alternatives | Find higher-rated alternatives in a category |
| clarvia_probe | Live probe — HTTP reachability, latency, OpenAPI, MCP, agents.json |

Setup Management

| Tool | Description |
|------|-------------|
| register_my_setup | Register your tool setup for AEO scoring per tool |
| compare_my_setup | Compare your setup against higher-scored alternatives |
| recommend_upgrades | Personalized upgrade recommendations |

Feedback & Support

| Tool | Description |
|------|-------------|
| clarvia_submit_feedback | Report tool usage outcomes for reliability data |
| clarvia_report_issue | Report bugs, request features, flag issues |
| clarvia_list_issues | List existing tickets and known issues |

---

Python MCP Server (24 tools)

The backend also runs a Python-based MCP server with extended capabilities:

| Tool | Description |
|------|-------------|
| search_services | Search indexed tools with advanced filters |
| scan_service | Full AEO audit |
| get_service_details | Detailed scoring breakdown |
| list_categories | Browse categories |
| get_stats | Platform statistics |
| register_service | Submit new service |
| clarvia_gate_check | Pass/fail safety gate |
| clarvia_batch_check | Batch URL checking |
| clarvia_find_alternatives | Category alternatives |
| clarvia_probe | Live accessibility probe |
| clarvia_submit_feedback | Report usage outcomes |
| clarvia_rescan | Trigger rescan of a profiled service |
| clarvia_get_rank | Get category ranking for a service |
| clarvia_get_feedback | Get community feedback for a service |
| clarvia_trending | Trending tools by score changes |
| clarvia_similar | Find similar tools to a given service |
| clarvia_audit | Audit npm/pip package dependencies |
| clarvia_featured | Get featured/curated tools |
| clarvia_demand | See most-requested tool categories |

Access via remote endpoint: https://clarvia-api.onrender.com/mcp/

---

Claude Code Skills

Pre-built skills for Claude Code that use Clarvia MCP tools:

| Skill | Command | Description |
|-------|---------|-------------|
| Scan | /clarvia-scan <url-or-name> | Run a full AEO audit on any tool |
| Compare | /clarvia-compare <tool-A> vs <tool-B> | Head-to-head dimension comparison |
| Recommend | /clarvia-recommend <use-case> | Get top tool picks for a use case |

Quick setup:

claude mcp add clarvia -- npx -y clarvia-mcp-server

cp .claude/skills/clarvia-*.md /your/project/.claude/skills/

See SKILLS.md for full installation and usage details.

---

REST API (110+ endpoints)

Full OpenAPI spec: /openapi.json

Key endpoints:

| Method | Endpoint | Description |
|--------|----------|-------------|
| GET | /v1/services | Search and filter services |
| GET | /v1/search | Full-text search |
| GET | /v1/score | Quick score lookup |
| GET | /v1/leaderboard | Top-scored services |
| GET | /v1/categories | Browse categories |
| POST | /v1/audit | Run AEO audit |
| GET | /v1/recommend | Intent-based recommendations |
| GET | /v1/similar/{id} | Find similar tools |
| GET | /v1/trending | Trending services |
| GET | /v1/featured | Curated picks |
| GET | /v1/stats | Platform statistics |
| GET | /v1/compare | Compare up to 4 tools |
| POST | /v1/profiles | Create service profile |
| GET | /v1/demand | Most-demanded categories |
| GET | /v1/feed/registry | Machine-readable feed for registries |

Rate limits: 10 scans/hour (free) · 100/hour (with X-API-Key)

---

Agent Discovery Endpoints

Clarvia is designed to be discovered by AI agents:

| Endpoint | URL |
|----------|-----|
| OpenAPI Spec | https://clarvia-api.onrender.com/openapi.json |
| agents.json | https://clarvia.art/.well-known/agents.json |
| llms.txt | https://clarvia.art/llms.txt |
| llms-full.txt | https://clarvia.art/llms-full.txt |
| robots.txt | https://clarvia.art/robots.txt |
| Sitemap | https://clarvia.art/sitemap.xml |
| MCP Endpoint | https://clarvia-api.onrender.com/mcp/ |

---

Architecture

scanner/
  backend/           # FastAPI (Python 3.12+) — 110+ API endpoints + MCP server
    app/
      checks/        # 13 scoring sub-factors
      routes/        # REST API endpoints
      services/      # Supabase, PDF generation, enrichment
      mcp_server.py  # Python MCP server (24 tools)
  frontend/          # Next.js + Tailwind — clarvia.art
  mcp-server/        # Node.js MCP server (TypeScript, 16 tools)
  cli/               # CLI scanner tool
  examples/          # Framework integration configs
  github-action/     # GitHub Actions for CI/CD AEO checks

Development

```bash

No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.

Install

Add to Claude Desktop or Cursor

{
    "mcpServers": {
        "clarvia": {
            "clarvia": {
                "command": "npx",
                "args": [
                    "-y",
                    "clarvia-mcp-server"
                ]
            }
        }
    }
}

More like this

Similar MCP servers you might find useful

Browse category

Git

A Model Context Protocol (MCP) server that provides tools for LLMs to read, search, and manipulate Git repositories. It enables automated repository…

88.1k
Developer Tools

Context 7

Official Context7 MCP server that brings up-to-date, version-specific library documentation and code examples into AI coding prompts.

58.7k
Developer Tools