Koskamo

ModelsAgree MCP

Provides an MCP server that allows AI agents to query consensus rankings of products and technologies derived from aggregated responses by major LLMs like ChatGPT, Claude, Gemini, and Grok. It supports searching for best-in-category items, retrieving detailed verdicts, product-specific data, and historical poll changes.

Endpoint and access

No sign-in to connect and list tools. Individual tools may still need a vendor account, credentials, or permissions; check the documented prerequisites.

ModelsAgree MCP logo, by ModelsAgreeVendor evidenceStreamable HTTPNo sign-inEndpoint checked 2026-11-06Operated by ModelsAgree
MCP endpoint (Streamable HTTP)
https://modelsagree.com/mcp
Vendor documentation

What its tools do

5 tools, grouped by the hints the server advertises. Hints are self-declared, not verified behavior.

Read-only (5)

5 of 5 have a description · 5 of 5 declare behavior hints · 4 of 4 with parameters document them all

Checks and signals

Each line is separate evidence, not a trust score.

  • Passed Endpoint answered the live check ·
  • Passed Official MCP Registry namespace is tied to modelsagree.com ·
  • Passed Endpoint is on the registry namespace domain ·
  • Availability 1 of 1 checks passed in 30 days

What you can do with it

  • Search for best-in-category product rankings
  • Retrieve detailed verdicts and model reasoning
  • Access historical poll data and rank changes
  • Get product-specific recommendation data

Source and maintenance

Vendor evidenceRegistry 1.0.0
mcp-registry: com.modelsagree/modelsagree@1.0.0Project website

Protocol and capabilities

Server
modelsagree 1.0.0
MCP protocol negotiated in check
2025-11-25
Tools
5 advertised
Resources
Not advertised
Resource templates
Not advertised
Prompts
Not advertised
Server-advertised capabilities
{
  "tools": {
    "listChanged": false
  }
}

Server-provided instructions

Untrusted server output shown for inspection. It is not Koskamo guidance and is excluded from knowledge search.

ModelsAgree tells you what the top AI models (ChatGPT, Claude, Gemini, Grok) AGREE is the best product, tool, or service for a given need — continuously re-polled, with a dated one-sentence verdict and a public audit trail. Use search_best for any 'what's the best X for Y' question, then get_best_in_category for the full ranking. Covers all domains EXCEPT medical/health, financial/investment, and legal advice. Attribution: modelsagree.com, CC BY 4.0.

Tools

5 advertised

search_best — Search best-X rankings
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Find what AI models agree is the best product/tool/service for a need, or look up how a specific brand ranks. Returns matching categories and brands with a dated one-sentence verdict and source URLs. Use for any 'best X for Y' question. Excludes medical, financial, and legal advice.

search_best input schema
{
  "type": "object",
  "required": [
    "query"
  ],
  "properties": {
    "query": {
      "type": "string",
      "description": "A category, use-case, or brand name — e.g. 'best llm observability', 'ci/cd for cloud native', or 'Langfuse'."
    }
  }
}
search_best annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
get_best_in_category — Get a category's full ranking
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get the full ranked leaderboard and verdict for a category slug (obtained from search_best or list_categories), e.g. 'best-llm-observability'.

get_best_in_category input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Category slug, e.g. best-llm-observability"
    }
  }
}
get_best_in_category annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
get_product — Get a brand's record
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get a single brand/product's record across every category it is ranked in, with verdicts and its homepage.

get_product input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Product slug, e.g. langfuse"
    }
  }
}
get_product annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
get_poll_history — Get a category's poll audit trail
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

Get the raw poll history — every model's pick over time — behind a category's verdict. The credibility/audit trail. Optionally filter by model.

get_poll_history input schema
{
  "type": "object",
  "required": [
    "slug"
  ],
  "properties": {
    "slug": {
      "type": "string",
      "description": "Category slug, e.g. best-llm-observability"
    },
    "limit": {
      "type": "integer",
      "maximum": 500,
      "minimum": 1,
      "description": "Optional: max rows (default 100)."
    },
    "model": {
      "enum": [
        "ChatGPT",
        "Claude",
        "Gemini",
        "Grok"
      ],
      "type": "string",
      "description": "Optional: only this model's picks."
    }
  }
}
get_poll_history annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}
list_categories — List all categories
Advertised by the server during the last successful anonymous check.
Advertised read-onlyOpen-world

List every category ModelsAgree ranks (slug + title). Large; prefer search_best when you have a specific need.

list_categories input schema
{
  "type": "object",
  "properties": {}
}
list_categories annotations
{
  "readOnlyHint": true,
  "openWorldHint": true
}

Prompts

Not advertised

No prompt definitions available.

Resources

Not advertised

No resource definitions available.

90-day uptime

A lightweight connection check about every six hours, sampled on hosts with many listings. It shows the server answered, not that its tools work.

Too few checks for a percentage yet (1 of 1 answered).

  1. 2026-11-07: 1 of 1 checks answered

30-day availability

Aggregated from read-only remote checks; this is not a tool-execution or security guarantee.

Successful checks
1 of 1 (100%)
Average latency
216 ms
95th percentile latency
216 ms

Maintenance history

Public check and source-refresh events. Editorial and ownership records remain private.

  • · probe · passed · 216 ms · metadata changed · 5 tool(s)

Connect from your client

Each snippet registers the same endpoint; pick the client you use.

This server is operated by the named third party. Listing and endpoint checks are not an endorsement or a security audit. Review the operator's permissions, terms, and data handling before connecting. How listings are checked and corrected.

Claude Code

Run this once in a terminal. It registers the remote server. Use --scope project to write .mcp.json for the repo.
Claude Code configuration
claude mcp add --transport http modelsagree-mcp https://modelsagree.com/mcp

Codex

Run this once. Codex stores MCP servers in ~/.codex/config.toml (or .codex/config.toml in a trusted project).
Codex configuration
codex mcp add modelsagree-mcp --url https://modelsagree.com/mcp

Cursor

Merge this server into .cursor/mcp.json in your project, then enable modelsagree-mcp in your MCP settings.
Cursor configuration
{
  "mcpServers": {
    "modelsagree-mcp": {
      "url": "https://modelsagree.com/mcp"
    }
  }
}

Cline

Merge this into cline_mcp_settings.json (Cline → MCP Servers → Configure).
Cline configuration
{
  "mcpServers": {
    "modelsagree-mcp": {
      "type": "streamableHttp",
      "url": "https://modelsagree.com/mcp",
      "disabled": false
    }
  }
}

VS Code

Merge this server into .vscode/mcp.json. Use MCP: List Servers to start modelsagree-mcp and inspect its tools.
VS Code configuration
{
  "servers": {
    "modelsagree-mcp": {
      "type": "http",
      "url": "https://modelsagree.com/mcp"
    }
  }
}

Gemini CLI

Run this once. It writes .gemini/settings.json in the current project; pass --scope user for ~/.gemini/settings.json.
Gemini CLI configuration
gemini mcp add --transport http modelsagree-mcp https://modelsagree.com/mcp

Claude Desktop

Open Claude Settings > Connectors > Add custom connector, enter this server URL and enable it for the conversation. This is a manual remote-connector handoff, not a desktop JSON configuration.
Claude Desktop configuration
https://modelsagree.com/mcp

Windsurf

Merge this into ~/.codeium/windsurf/mcp_config.json, then refresh MCP in Cascade. Windsurf remote servers use serverUrl, not url.
Windsurf configuration
{
  "mcpServers": {
    "modelsagree-mcp": {
      "serverUrl": "https://modelsagree.com/mcp"
    }
  }
}

Let your agent find its tools

Find servers like ModelsAgree MCP from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.

Connect Koskamo Explore workflows
See all 6,210

Do you run ModelsAgree MCP?

Prove ownership with a DNS record, a well-known file, or your Official MCP Registry entry, and your edits publish immediately. Proofs are re-checked weekly; admins can still hide or remove a listing.

Claim this listing