← Registry

Developer Tools

agentery.com

Provides a directory and benchmarking tools for discovering and comparing AI agents for workflow automation.

1 endpoint19 known toolsFirst detected July 25, 2026Last detected August 29, 2026

ENDPOINT 1

https://agentery.com/api/mcp

No auth detected

MCP server metadata

Name
agentery
Version
1.8.0
Capabilities
toolsresourcesprompts
Server instructions

Agentery (agentery.com) is the live market-intelligence layer for the commercial agent economy, covering both AI agents and MCP servers. Typical flow for choosing a provider by capability and value-for-money: research_capability (ONE call — resolves the market, current pricing/index context and a ready-to-compare provider shortlist; the fastest path) or the lower-level search_providers (free-text + price filters) -> compare_providers (shortlist side by side with upvotes) -> get_provider_profile (full evidence-scored profile) -> suggest_alternatives (substitutes when the pick is too expensive or unreachable; cheaper_only to shop down). Search/profile/compare cards carry a `liveness` object (daily endpoint probe: alive, latency, 7-day uptime); profile/compare cards also carry `reported_success` — the machine-reported outcome rate from report_outcome (null until 5+ distinct correlated reporters in 90 days). After you USE a listed provider, call report_outcome (worked|failed|partial): reports are correlated with your recent retrievals, sharpen rankings, and 5+ correlated reports in 30 days doubles your rate limit. To scope pricing to one delivery type, pass provider_type=agent|mcp to get_price_index / price_benchmark — agents and MCP servers price differently. For market research: market_gaps lists demand-first whitespace (clusters of real user requests far from any paid provider), market_report deep-dives one market from a natural-language query (pricing by provider type and buyer tier + top providers), price_benchmark gives per-persona price distributions plus an Provider-vs-MCP split, demand_signals lists capability queries that returned zero results here (live unmet demand). For price MOVEMENT: get_price_index returns the current Agent Economy Price Index (AEPI) level with 1d/7d/30d change for the whole economy and each buyer tier — and get_price_index_history returns the dated series to chart it (the same chained like-for-like index the /aepi page shows; an index level, never a market price). get_provider returns the public directory card. For a NEW procurement or market-research request, call research_capability FIRST (one call: market + pricing/index + a compare-ready provider shortlist) unless the user already gave a known market or provider list. rank_providers_for_workflow (ranked candidates per workflow step) is partner-only and needs a Bearer key. Public tools are rate-limited to 30 calls/min per IP (60 for outcome contributors).

Known tools 19

research_capability

START HERE for provider procurement.

Inferred read-only
search_providers

Targeted 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.

Inferred read-only
find_market

Map 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).

Inferred read-only
compare_providers

Call this to decide between shortlisted providers.

Inferred read-only
get_price_index

Call 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).

Inferred read-only
price_benchmark

Fair-price benchmarks for a capability described in natural language.

Inferred read-only
get_price_index_history

Call 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.

Inferred read-only
market_gaps

Find where real demand is going unmet — computed demand-first in the raw text-embedding space (NO fixed categories).

Inferred read-only
suggest_alternatives

Call 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 lookup) — each with observed price, endpoint liveness, community upvotes and how_to_connect (website, docs, mcp endpoint) so a substitute is immediately usable.

Inferred read-only
demand_signals

Call 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.

Inferred read-only
report_outcome

After 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.

Inferred read-only
rank_providers_for_workflow

PARTNER-ONLY (Bearer key required).

Inferred read-only
get_provider_profile

Call 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, trust signals, evidence_quality, entity_type, regulated_data_suitability, evidence_urls, last_checked.

Inferred read-only
get_provider

Call 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.

Inferred read-only
market_report

Deep-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).

Inferred read-only
create_custom_benchmark

Create a PRIVATE custom benchmark (a saved, calculated peer cohort) over Agentery's data — no account needed.

Potential side effects
get_custom_benchmark

Get 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 cohorts, historical index, and data coverage.

Inferred read-only
update_custom_benchmark

Add/remove members or rename a custom benchmark.

Potential side effects
delete_custom_benchmark

Disable access to a custom benchmark.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.agentery]
url = "https://agentery.com/api/mcp"
enabled = true
Claude Code

.mcp.json

{
  "mcpServers": {
    "agentery": {
      "type": "http",
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Claude Desktop

Settings → Connectors → Add custom connector

Name: agentery
Remote MCP URL: https://agentery.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "agentery": {
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code
{
  "servers": {
    "agentery": {
      "type": "http",
      "url": "https://agentery.com/api/mcp"
    }
  }
}
Generic MCP

Client-specific MCP configuration

{
  "name": "agentery",
  "transport": "streamable-http",
  "url": "https://agentery.com/api/mcp"
}
MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for agentery.com was fetched 2026-08-25T23:21:25.034Z.

Trust status New

This domain appears to have previously been parked, so its current status is new or unverified.

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.