Skip to main content

MCP Server

Connect your favorite AI tools to the Agentic Developer Tools Radar via our Model Context Protocol (MCP) server endpoint. Access real-time tool evaluations, timeline events, and intelligence data from any MCP-compatible client.

Use the guides below to connect your platform to our MCP server and start querying the radar data programmatically.

Integration Guides

Claude Desktop

  1. Open the application and navigate to Settings.
  2. Select the MCP Servers section.
  3. Click Add Server and paste the configuration below.
  4. Save and restart the application to connect.
{
  "mcpServers": {
    "ai-radar": {
      "url": "https://ai-research.wwtdigital.com/api/mcp/mcp"
    }
  }
}

ChatGPT

  1. Open Settings and go to MCP Plugins.
  2. Click Add MCP Server.
  3. Paste the configuration below and confirm.
{
  "mcpServers": {
    "ai-radar": {
      "url": "https://ai-research.wwtdigital.com/api/mcp/mcp"
    }
  }
}

Windsurf

  1. Open settings via the gear icon.
  2. Navigate to Extensions > MCP.
  3. Add a new server with the configuration below.
{
  "mcpServers": {
    "ai-radar": {
      "url": "https://ai-research.wwtdigital.com/api/mcp/mcp"
    }
  }
}

Claude Code

  1. Open your project settings.
  2. Add the MCP server configuration below to your .mcp.json file.
  3. Restart the application to apply.
{
  "mcpServers": {
    "ai-radar": {
      "url": "https://ai-research.wwtdigital.com/api/mcp/mcp"
    }
  }
}

Slack

Custom

Custom setup guide. Use the MCP endpoint to query radar data from bots or workflows.

Endpoint: Send POST requests to the MCP endpoint at https://ai-research.wwtdigital.com/api/mcp/mcp

Example request payload:

{
  "method": "tools/list",
  "params": {}
}

Teams

Custom

Custom setup guide. Connect via the MCP endpoint to surface radar data in channels.

Endpoint: Send POST requests to the MCP endpoint at https://ai-research.wwtdigital.com/api/mcp/mcp

Example request payload:

{
  "method": "tools/list",
  "params": {}
}

Glean

Custom

Custom setup guide. Use the MCP endpoint to index radar data in your search instance.

Endpoint: Send POST requests to the MCP endpoint at https://ai-research.wwtdigital.com/api/mcp/mcp

Example request payload:

{
  "method": "resources/list",
  "params": {}
}

Tools Library

* required

search_tools

Search Tools

Search the agentic tools radar using semantic search. Returns tools matching the query with similarity scores.

Reference

querystring*

Natural language search query

limitnumber

Maximum results to return (default: 5)

Examples

  • Search for code review tools
  • Find IDE tools with strong governance

Try It Playground

Prompting Tips

Do

  • Use natural language queries that describe the capability you want.
  • Add a category or context when you want narrower results.

Don't

  • Do not use internal IDs when a plain-language query will do.
  • Do not ask for more results than you plan to review.

get_tool_details

Get Tool Details

Get detailed information about a specific tool including scores, dimensions, status, and history.

Reference

toolIdstring

Exact tool ID

toolNamestring

Tool name (case-insensitive)

Examples

  • Get details for Cursor

Try It Playground

Prompting Tips

Do

  • Prefer toolId when you already have the exact identifier.
  • Use toolName for a quick follow-up after a search result.

Don't

  • Do not provide both toolId and toolName unless you need a fallback.

compare_tools

Compare Tools

Compare 2-3 tools side by side across all dimensions. Highlights governance differences and key differentiators.

Reference

toolIdsstring*

Comma-separated tool IDs (2-3)

Examples

  • Compare Cursor and Copilot

Try It Playground

Prompting Tips

Do

  • Compare two or three tools at a time for readable output.
  • Use tool IDs returned from search_tools for exact matches.

Don't

  • Do not compare large groups of tools in a single request.
  • Do not mix unrelated categories unless that contrast is the point.

get_risky_tools

Get Risky Tools

Find tools with governance gaps, security concerns, or CAUTION or CRITICAL markers.

Reference

severityenum

Filter by risk severity

lowGovernanceOnlyboolean

Only tools with governance below 12/18 threshold

limitnumber

Max results

Examples

  • Show critical-risk tools

Try It Playground

Prompting Tips

Do

  • Filter by severity when you need a short triage list.
  • Use lowGovernanceOnly when governance is your primary screening factor.

Don't

  • Do not treat an empty result as proof that all tools are equally safe.

get_trending_tools

Get Trending Tools

Find tools with recent rating changes. Filter by trend direction.

Reference

directionenum

Filter by trend direction

limitnumber

Max results

Examples

  • Show newly added tools

Try It Playground

get_recommendations

Get Recommendations

Get top-rated tool recommendations. Filter by category or status level.

Reference

categorystring

Filter by category name

statusFilterenum

Filter by maturity status

limitnumber

Max results

Examples

  • Recommend adopted coding assistants

Try It Playground

Prompting Tips

Do

  • Use category when you already know the workflow you are shopping for.
  • Use statusFilter to align results with your adoption appetite.

Don't

  • Do not rely on recommendations alone when governance concerns are material.

get_timeline_events

Get Timeline Events

Browse the industry timeline of major events in agentic developer tools.

Reference

typeenum

Filter by event type

minSignificancenumber

Minimum significance level (1-5)

limitnumber

Max events to return

querystring

Keyword filter on title or description

Examples

  • Show major product launches with significance 4 or higher

Try It Playground

Prompting Tips

Do

  • Use minSignificance to keep the timeline focused on major changes.
  • Add a query when you are tracking a specific company or theme.

Don't

  • Do not ask for the entire timeline when a smaller slice will answer the question.

get_tool_history

Get Tool History

Get the version history and score changes for a specific tool over time.

Reference

toolIdstring

Tool UUID

toolNamestring

Tool name (case-insensitive)

Examples

  • Show Cursor history

Try It Playground

Prompting Tips

Do

  • Use this after get_tool_details when you want change-over-time context.
  • Ask for history on a single tool at a time.

Don't

  • Do not expect comparison output here; use compare_tools for side-by-side analysis.

get_insights

Get Insights

Get radar-wide insights and statistics including tool counts, averages, and top tools.

Examples

  • Summarize the current radar

Try It Playground

Prompting Tips

Do

  • Use this when you want a quick snapshot of the whole radar.
  • Follow up with narrower tools when an aggregate number raises questions.

Don't

  • Do not expect detailed per-tool analysis in this aggregate view.

submit_tool

Submit Tool

Submit a new agentic developer tool for evaluation. Creates a GitHub issue.

Reference

toolstring*

Tool name

productUrlstring*

URL to the product page

quickTakestring*

Brief description or elevator pitch

Examples

  • Submit a new evaluation candidate

Try It Playground

Prompting Tips

Do

  • Provide a clear product URL and a concise quick take.
  • Use this when the tool is not already present in the radar.

Don't

  • Do not include sensitive data in the submission fields.
  • Do not use placeholder URLs for real submissions.

get_intel_sources

Get Intel Sources

Search the ai-intel source archive. Returns ingested AI market news.

Reference

querystring

Keyword filter on title or summary

categorystring

Filter by category

relevanceenum

Filter by relevance level

limitnumber

Max results

Examples

  • Find recent high-relevance coding assistant coverage

Try It Playground

Prompting Tips

Do

  • Use relevance to surface the most strategic items first.
  • Combine query and category when you need targeted market scans.

Don't

  • Do not use overly broad queries if you want only a few sources.

get_intel_briefings

Get Intel Briefings

Get recent weekly intelligence digests from the ai-intel pipeline.

Reference

limitnumber

Number of recent digests to return

Examples

  • Show the three latest weekly digests

Try It Playground

Prompting Tips

Do

  • Use a small limit when you want a concise weekly recap.
  • Use this when source-level detail is less important than synthesized themes.

Don't

  • Do not expect raw source snippets here; use get_intel_sources for that.

search_intel

Search Intel

Unified keyword search across the ai-intel source archive and weekly digests.

Reference

querystring*

Search query

limitnumber

Max results per category

Examples

  • Search intel for reasoning model launches

Try It Playground

Prompting Tips

Do

  • Use a focused phrase when you want sources and briefings on the same topic.
  • Start here when you are not sure whether to browse sources or digests.

Don't

  • Do not treat this as a substitute for tool-specific radar queries.