ModelsAgree
Measured conclusion: Deep-tested. L2 outcome: tools_ok.
Consensus 'best X for Y' rankings from ChatGPT, Claude, Gemini & Grok. Search, verdicts, history.
| Author | com.modelsagree |
|---|---|
| Access | remote |
| Publisher key required | No |
| Measured state | Deep-tested |
| L1 liveness | alive |
| L1 latency | 2080 ms |
| Last measured | 2026-10-26 |
Add to your agent
Copy this into your MCP client config:
{
"mcpServers": {
"ModelsAgree": {
"url": "https://modelsagree.com/mcp",
"transport": "streamable-http"
}
}
}
Measured tools (5)
search_bestread-onlyFind 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.
Parameters:
query(required) — string — A category, use-case, or brand name — e.g. 'best llm observability', 'ci/cd for cloud native', or 'Langfuse'.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes
get_best_in_categoryread-onlyGet the full ranked leaderboard and verdict for a category slug (obtained from search_best or list_categories), e.g. 'best-llm-observability'.
Parameters:
slug(required) — string — Category slug, e.g. best-llm-observability
Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes
get_productread-onlyGet a single brand/product's record across every category it is ranked in, with verdicts and its homepage.
Parameters:
slug(required) — string — Product slug, e.g. langfuse
Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes
get_poll_historyread-onlyGet the raw poll history — every model's pick over time — behind a category's verdict. The credibility/audit trail. Optionally filter by model.
Parameters:
slug(required) — string — Category slug, e.g. best-llm-observabilitylimit— integer — Optional: max rows (default 100).model— string — Optional: only this model's picks.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes
list_categoriesread-onlyList every category ModelsAgree ranks (slug + title). Large; prefer search_best when you have a specific need.
Hints: read-only yes · destructive not declared · idempotent not declared · open-world yes
Measured by MCPYP probing. Untested fields are omitted, never estimated. Listing is always free; MCPYP never proxies calls or stores user tokens.