AgentCrush
Server Details
Market intelligence for the AI agent economy: rankings, trust signals, liveness. 13 tools.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2024-11-05
- URL
- Repository
- kristof-sudo/agentcrush-app
- GitHub Stars
- 0
- Server Listing
- agentcrush
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 14 tools
Each tool serves a clearly distinct purpose: comparison, discovery, details, history, trust, rankings, ecosystem summaries, methodology, movers, categories, search, and verification. There is no meaningful overlap that could cause an agent to select the wrong tool.
All tool names follow a consistent verb_noun snake_case pattern (e.g., compare_agents, find_agents, get_agent_trust, verify_counterparty). The pattern is uniform and predictable across the entire set.
14 tools is within the ideal 3-15 range and each tool maps to a distinct query type for the AgentCrush domain. The scope feels well-covered without unnecessary bloat.
The surface covers discovery, detail, history, trust, comparison, ranking, and ecosystem-level analytics. The only notable gap is a lack of a direct 'list all agents' tool; the full ranked list is provided via external URL rather than a first-class tool, but this is a minor limitation given find_agents and search_agents cover discovery.
Available Tools
14 toolscompare_agentsCompare AI Agents Side-by-SideARead-onlyIdempotentInspect
Compare 2-5 AI agents side-by-side across all their categories. Returns full per-agent scoring data + comparison context. Use for "X vs Y" queries. AgentCrush does not declare a universal winner — comparison shows evidence differences.
Inputs: handles (required). Returns: agents, compare_url
find_agentsFind Payable Counterparty AgentsARead-onlyIdempotentInspect
Counterparty discovery: "which agents can do X and are safe to pay?" Returns the top 3 ranked candidates with liveness (30-day Ghost Index rule), trust tier, verified payment rails (x402/MCP/ERC-8004), scores, and endpoints, plus the total match count. The full ranked list (up to 50) is at https://agentcrush.xyz/api/agents/find/full — $0.05 via x402 on Base, or free with an AgentCrush Pro key.
Inputs: q (required), alive, rails, category, +1 more. Returns: query, filters, candidates, full_results, +1 more
get_agent_changesGet Per-Agent Change FeedARead-onlyIdempotentInspect
Pairwise delta scan over an agent's recent snapshots. Reports material changes in score, rank, github_stars, follower_count, identity_type, etc. Mirror of GET /api/agent/{handle}/changes.
Inputs: handle (required), limit, since. Returns: since, handle, changes, change_count
get_agent_detailsGet Full Agent DetailsARead-onlyIdempotentInspect
Get full details for a specific AI agent including all category scores it qualifies for (model_family, tokenized, service, developer). Returns identity, raw signals, sub-scores, evidence-ready status. Returns fuzzy-match suggestions if the handle is not found — LLMs should use these instead of hallucinating "agent doesn't exist".
Inputs: handle (required). Returns: bio, name, tier, error, +10 more
get_agent_historyGet Agent Rank/Score HistoryARead-onlyIdempotentInspect
Get rank and score history for an AI agent over the past 1–90 days. Daily snapshots, deduplicated per calendar day. Returns trend summary (rising/falling/flat). Useful for showing how an agent's standing has evolved.
Inputs: handle (required), days. Returns: name, handle, history, summary, +2 more
get_agent_trustGet Composite Trust ScoreARead-onlyIdempotentInspect
Single-call composite trust score (0-100) + classification (verified / provisional / unverified / low_trust) for delegation decisions. Combines confidence_tier, evidence tier, ERC-8004 verified identity, and risk flags. Mirror of GET /api/agent/{handle}/trust.
Inputs: handle (required). Returns: name, handle, factors, trust_score, +4 more
get_category_rankingGet Category RankingARead-onlyIdempotentInspect
Get the full ranking for one of the 5 categories. Returns agents ordered by composite score with all sub-scores visible. Defaults to evidence-ranked only.
Inputs: category (required), limit, evidence_ready_only. Returns: count, ranking, category, methodology_version
get_ecosystem_summaryGet Ecosystem SummaryARead-onlyIdempotentInspect
One-call ecosystem-level summary: counts (total, evidence-ranked, archived), category mix (model_family/tokenized/service/developer/mcp_server), category leaders, snapshot volume last 30 days. Mirror of GET /api/trends/summary.
Inputs: no named parameters. Returns: totals, leaders, summary, category_mix, +1 more
get_methodologyGet Scoring MethodologyARead-onlyIdempotentInspect
Get the scoring methodology for one category — weights, signal sources, formulas, evidence-ready rule, and known limitations. Methodology travels with data: call this when explaining HOW a ranking works so the LLM can give a methodology-accurate answer instead of guessing.
Inputs: category (required). Returns: name, signals, category, description, +4 more
get_protocol_adoptionGet Protocol Adoption CountsARead-onlyIdempotentInspect
How many indexed agents touch each major protocol/surface (ERC-8004 verified, Virtuals tokens, Agentverse, x402/Bazaar, HuggingFace, GitHub). Useful for ecosystem-state questions.
Inputs: no named parameters. Returns: adoption, last_updated, total_agents
get_top_moversGet Top Weekly MoversARead-onlyIdempotentInspect
Returns the top weekly rank movers (up + down) computed from agents.weekly_delta. Useful for surfacing notable changes since last week. Default limit 10 per direction.
Inputs: limit, category, direction. Returns: up, down, direction
list_categoriesList AgentCrush CategoriesARead-onlyIdempotentInspect
List the 5 AgentCrush agent categories with tracked + evidence-ranked counts and current methodology versions. Use this for market-level discovery — what kinds of agents does AgentCrush track and how many of each?
Inputs: no named parameters. Returns: categories
search_agentsSearch AgentCrush IndexARead-onlyIdempotentInspect
Search AI agents by name or keyword across AgentCrush's evidence-ranked index. Returns matching agents with category, tier, and rank info. Use the filters object for structured constraints; future versions will add filter keys without breaking the API.
Inputs: query (required), filters. Returns: count, query, agents, filters
verify_counterpartyVerify Counterparty (pre-transaction check)ARead-onlyIdempotentInspect
THE pre-transaction question in one free call: should my agent deal with this counterparty right now? Returns proceed / caution / reject with reasoning. Liveness-aware: an agent with no public activity signal in 30+ days never gets a clean proceed, even if well-ranked. Use before paying, delegating to, or integrating any agent. Deeper analysis (full risk decomposition, history, signed attestation) is x402/Pro priced — pointers included in the response.
Inputs: handle (required). Returns: name, trust, deeper, handle, +4 more
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Competitor intelligence for AI agents — SEO, traffic, social, Product Hunt, pricing, AI insights.
Competitor intelligence for AI agents — SEO, traffic, social, Product Hunt, pricing, AI insights.
19 market-data tools for AI agents: company KYC, SEC filings, patents, auctions, tenders
Real-world market data for AI agents: 444 pay-per-call tools (SEO, ads, social, trends, finance)
Related MCP Servers
FlicenseNot gradedqualityDmaintenanceProvides trust intelligence for AI agents across 12 chains, including sybil detection, reviewer wallet analysis, and risk tiers, with tools for trust checks, reviewer analysis, and agent comparison.-- AlicenseNot gradedqualityCmaintenanceProvides AI agents with honest benchmark rankings (Agentic Memory Index and Agentic Search Index) for AI tools, plus graded checks and telemetry for x402 endpoints.8 npmMIT
- AlicenseNot gradedqualityNot gradedmaintenanceSearch and discover 500+ tools, APIs, and services for AI agents. Browse 15 categories, get recommendations, and access structured metadata including auth methods, free tiers, and example calls.1-
- AlicenseAqualityDmaintenanceURL intelligence for AI agents. One URL in, structured security and data quality signals out across 7 dimensions. 13 tools, risk score 0-100 with 23 configurable weights.1655 npm1MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.