Index / MCP servers / Agentery

Agentery MCP server

Connect Agentery and your agent gets 19 tools, among them compare_providers, create_custom_benchmark, delete_custom_benchmark. It answers at https://agentery.com/api/mcp over streamable HTTP, and it listed its tools to an anonymous client, so no sign-in was needed for that. Our probes reached it 8 of 10 times since 4 September 2026; the last check, on 17 October 2026, succeeded.

Status
Answering
Tools
19
Official
yes, served from agentery.com
Reliability
8 of 10 checks
Response time
156 ms
Transport
streamable HTTP
Last checked
17 October 2026

Find and compare 39,000+ AI agents, MCP servers and APIs, with daily prices and the AEPI price index

Description as the publisher wrote it.

The 19 tools Agentery offers

ToolWhat it does
compare_providersCall this to decide between shortlisted providers. Inputs are resolved to REAL providers — exact handle, then exact display name — and are NEVER silently swapped for a fuzzy match: unknown inputs come back in `unresolved_inputs` with `sugge
Inputs: provider_ids
create_custom_benchmarkCreate a PRIVATE custom benchmark (a saved, calculated peer cohort) over Agentery's data — no account needed. Two modes: (A) explicit members: pass `members` (a list of exact handles; product names/domains resolve where unambiguous). (B) fo
Inputs: name, members, base_niche, remove, add, allow_partial
delete_custom_benchmarkDisable access to a custom benchmark. Keeps only a minimal audit record; no underlying Agentery data is touched. Pass `benchmark_id`.
Inputs: benchmark_id
demand_signalsCall this to see what providers are being SEARCHED FOR but don't exist yet: capability queries that returned ZERO results on this MCP server, aggregated and ranked by miss count. A live unmet-demand signal for founders and investors — pair
Inputs: limit
find_marketMap a natural-language task, capability or service to its live MARKET — the semantic neighbourhood of the closest-matching providers, found by text-embedding nearness (NO fixed category). For buyers ('a provider that monitors competitor pri
Inputs: task, query
get_custom_benchmarkGet a private custom benchmark's current report: members, current stats (headline median/quartiles only when ≥3 comparable priced members — monthly, per-seat and per-call prices are never blended), buyer-tier / provider-type / pricing-unit
Inputs: benchmark_id, version, as_of, response_mode
get_price_indexCall this for the CURRENT level of the Agent Economy Price Index (AEPI) — a chained like-for-like index over observed provider/MCP pricing (base 100 = 29 Jun 2026). It is an INDEX LEVEL, not a market price or tradeable asset. Returns the wh
Inputs: provider_type, tier, response_mode
get_price_index_historyCall this for the canonical DATED index SERIES (to chart or analyse movement) of the AEPI — the same chained like-for-like series the /aepi page plots. Every point is an index level (base 100), never a price. Returns the whole-economy headl
Inputs: provider_type, tier, period, response_mode
get_providerCall this for the public directory card of one provider by handle or registration number: bio, source URLs, X-verification status, entity type, community rating and structured profile when available.
Inputs: handle, regNum
get_provider_profileCall this to drill into ONE provider after search_providers or compare_providers: full evidence-scored profile — task_performed, inputs/outputs, integrations, protocols, industry_fit, autonomy_level, human_approval_needed, observed price, t
Inputs: provider_id
market_gapsFind where real demand is going unmet — computed demand-first in the raw text-embedding space (NO fixed categories). A gap = a cluster of real user requests (mined from live MCP search telemetry) that sits FAR from any PAID provider. For ea
Inputs: sector, rank, limit
market_reportDeep-dive ONE market before building or investing — the market is the semantic neighbourhood of your natural-language query (nearest providers by text embedding, NO fixed category). Every field is MEASURED: the observed-pricing benchmark se
Inputs: query, response_mode
price_benchmarkFair-price benchmarks for a capability described in natural language. The MARKET is the semantic neighbourhood of your query — the nearest providers by text embedding, with NO fixed category — SEPARATED BY provider type (provider / mcp) and
Inputs: niche, sector, provider_type, buyer_tier, pricing_unit, response_mode
rank_providers_for_workflowPARTNER-ONLY (Bearer key required). Given a business context and its workflow steps, return ranked provider candidates for EACH step — structured, scored (match_score 0-100) matches with match_reasons and cautions. Built for app builders (e
Inputs: business_context, workflow_steps, limit_per_step
report_outcomeAfter you use a listed provider, report whether it worked — reports are correlated with your recent retrievals, improve ranking accuracy, and unlock higher rate limits for contributors. Only reports we can match to one of YOUR retrievals (s
Inputs: agent_id, outcome, task_type, error_class, latency_ms, note
research_capabilitySTART HERE for provider procurement. ONE call turns a task into: (1) its live MARKET — the semantic neighbourhood of the closest-matching providers, found purely by text-embedding nearness (NO fixed category), with the relevance floor and h
Inputs: task, buyer_tier, max_monthly_usd, integrations, sort, limit
search_providersTargeted provider search when you already know roughly what you want; for a NEW task where the market isn't known yet, call research_capability first. Filtered free-text search over the directory, ranked with match_score and match_reasons.
Inputs: query, filters, max_monthly_usd, require_public_price, billing, sort
suggest_alternativesCall this when a shortlisted provider is too expensive, unreachable or a poor fit: substitutes for one known provider, ranked by text-embedding nearness to that provider's OWN profile — the closest-matching providers first (NO category look
Inputs: agent_id, cheaper_only, limit
update_custom_benchmarkAdd/remove members or rename a custom benchmark. Creates a NEW immutable version (the previous version stays fully reproducible) and returns the exact change-impact on the median/quartiles/index. Pass `benchmark_id`.
Inputs: benchmark_id, add, remove, rename

Add Agentery to your AI client

Every block below points at https://agentery.com/api/mcp. Pick your client and copy.

Claude Code: one command in your terminal
claude mcp add --transport http agentery https://agentery.com/api/mcp
Claude Desktop: claude_desktop_config.json
{
  "mcpServers": {
    "agentery": {
      "command": "npx",
      "args": ["-y", "mcp-remote", "https://agentery.com/api/mcp"]
    }
  }
}
Cursor: ~/.cursor/mcp.json, or .cursor/mcp.json in a project
{
  "mcpServers": {
    "agentery": {
      "url": "https://agentery.com/api/mcp"
    }
  }
}
VS Code and GitHub Copilot: .vscode/mcp.json
{
  "servers": {
    "agentery": {
      "type": "http",
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Zed: Zed settings.json
{
  "context_servers": {
    "agentery": {
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Windsurf: ~/.codeium/mcp_config.json
{
  "mcpServers": {
    "agentery": {
      "serverUrl": "https://agentery.com/api/mcp"
    }
  }
}
JetBrains AI Assistant: Settings, Tools, AI Assistant, MCP, New MCP Server, as JSON
{
  "mcpServers": {
    "agentery": {
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Continue: .continue/mcpServers/neuronto.yaml
name: Agentery
version: 0.0.1
schema: v1
mcpServers:
  - name: Agentery
    type: streamable-http
    url: https://agentery.com/api/mcp
Gemini CLI: ~/.gemini/settings.json
{
  "mcpServers": {
    "agentery": {
      "httpUrl": "https://agentery.com/api/mcp"
    }
  }
}
Codex CLI: MCP server config
{
  "mcpServers": {
    "agentery": {
      "type": "http",
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Warp: MCP servers, + Add, paste JSON
{
  "mcpServers": {
    "agentery": {
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Goose: a one-click extension link
goose://extension?url=https%3A%2F%2Fagentery.com%2Fapi%2Fmcp&type=streamable_http&id=agentery&name=Agentery

Is Agentery up right now?

It answered our last check on 17 October 2026 in 156 ms. Over 10 checks since 4 September 2026 it answered 8. Status here comes from Neuronto's own probes, not from the publisher.

MCP servers similar to Agentery

Questions about Agentery

Is there an official Agentery MCP server?

Yes. It is published by agentery.com and served from agentery.com, the vendor's own domain: https://agentery.com/api/mcp.

How many tools does Agentery have?

19, as returned by the server's own tools/list on 9 September 2026: compare_providers, create_custom_benchmark, delete_custom_benchmark, demand_signals, find_market, get_custom_benchmark, get_price_index, get_price_index_history, and 11 more.

Is Agentery down?

It answered our last check on 17 October 2026 in 156 ms. Over 10 checks since 4 September 2026 it answered 8.

How do I add Agentery to Cursor?

Put the server under mcpServers in ~/.cursor/mcp.json with the URL https://agentery.com/api/mcp. The exact JSON is above, with the same setup for Claude Code, Claude Desktop, VS Code, Windsurf, Zed, Gemini CLI and the rest.

Does Agentery need an API key?

It listed its tools to an anonymous client, so reading the tool list needs no key. Individual tools can still ask for credentials in their own inputs.

Where this comes from

Publisher: com.agentery. Endpoint host: agentery.com. ARD identifier: urn:air:com.agentery:mcp:agentery. First indexed 31 August 2026. The tools are exactly what the server returned; nothing on this page is inferred from its name. Ranking in Neuronto search is never for sale.

Is this your server? Get a message the day it stops answering or its tools change: monitoring, 14 days free. Or claim the domain to manage how it is listed.