Skip to content
Migrate your GPTCheck my InvokeRank
InvokeIndex

The tools agents can call

165,873 unique MCP servers across ten major directories and registries, each with its sources and history.

Each server counts once, however many directories list it. Glama, PulseMCP and mcp.so listings arrive through MCP Toplist’s open dataset, used under CC BY 4.0. 14,806 listings from bulk publishers wait for review.

Check my InvokeRankUpdated How we collect
  • Directory listings71,387Collected from seven directories, before grouping
  • Listed in two or more36,04922% of unique servers
  • Remote MCP servers32,569With a public endpoint an agent can call
  • Changes, last 30 days154,639Typed diffs between observations

Glama (102,258)

Plus 338 listings grouped under these serversPage 565 of 4,261
Inside the index

Where the servers are listed

Each directory is a shelf. See how many shelves each server sits on, how large each shelf is, and what moved this month.

Updated

How many shelves

Servers by the number of directories listing them

78%of servers are listed in one directory only. 36,049 are listed in two or more.

Directories listing the server. Copies grouped under a server are not counted again.

The shelves

Unique servers listed in each directory
  1. Glama102,258
  2. MCP Registry45,897
  3. PulseMCP22,401
  4. mcp.so19,350
  5. Smithery14,503
  6. ChatGPT8,262
  7. Claude7,004
  8. GitHub597
  9. Cursor471
  10. Claude Code337

Collected by us Via MCP Toplist’s dataset

A server listed in several directories counts once in each. Pick a shelf to browse it.

What changed

Typed diffs between observations, last 30 days
New listings 20,296Left a directory 808Tool changes 110,767Listing details 22,768The busiest day was 15 Oct, with 10,748 changes.
Changes by day, last 30 days (days with changes)
DayNew listingsLeft a directoryTool changesListing details
2 Oct26540140
3 Oct647203212969
4 Oct51463265441
5 Oct942293912615
6 Oct6461559201698
7 Oct7372250891699
8 Oct7042415021864
9 Oct16671759321572
10 Oct13976049091137
11 Oct5272150281634
12 Oct7532044771770
13 Oct871215291627
14 Oct853284194665
15 Oct1276208675777
16 Oct11111038540842
17 Oct1066175225830
18 Oct669216954725
19 Oct1859926805986
20 Oct895134874756
21 Oct1163857641369
22 Oct9441857741895
23 Oct790121906757

Latest changes

RSS feed
  1. Hotel Booking AI MCP Official MCP Registry search_location: input schema changed
  2. Hotel Booking AI MCP Official MCP Registry search_location: description changed (+"普通 ToC 酒店查询可匿名，user_key 可选；下单、订单查询、取消和支付需要客户端安全配置的 user_key。 先用此工具解析用户地点/酒店名，再用返回的 ID 或坐标搜索酒店；不得编造 ID。 查询失败时先区分参数/鉴权错误和上游暂时失败：修正参数或重新授权后再调用，仅暂时失败可有限重试；不得把错误或空结果改述成成功。")
  3. Hotel Booking AI MCP Official MCP Registry search_location: annotations changed
  4. Hotel Booking AI MCP Official MCP Registry search_hotels: input schema changed
  5. Hotel Booking AI MCP Official MCP Registry search_hotels: description changed (+"普通 ToC 酒店查询可匿名，user_key 可选；下单、订单查询、取消和支付需要客户端安全配置的 user_key。 任一非 null 坐标参数会选择坐标模式，必须齐全提供经纬度与正半径；否则非空 keyword 走模糊匹配，否则必须给 region_id。区域/坐标结果已实时筛选，关键词结果仅供定位。预算最终按验价总价核对，不能用每晚参考价代替订单总价。 查询失败时先区分参数/鉴权错误和上游暂时失败：修正参数或重新授权后再调用，仅暂时失败可有限重试；不得把错误或空结果改述成成功。")
  6. Hotel Booking AI MCP Official MCP Registry search_hotels: annotations changed
  7. Hotel Booking AI MCP Official MCP Registry query_room_rates: input schema changed
  8. Hotel Booking AI MCP Official MCP Registry query_room_rates: description changed (+"普通 ToC 酒店查询可匿名，user_key 可选；下单、订单查询、取消和支付需要客户端安全配置的 user_key。 先确定酒店和入住条件，返回 data.room_types[].products；选择符合成人/儿童和餐食政策的报价后验价。产品摘要未提供 maxChildren，缺失不等于不接待儿童，必须按实际儿童人数/年龄验价。 查询失败时先区分参数/鉴权错误和上游暂时失败：修正参数或重新授权后再调用，仅暂时失败可有限重试；不得把错误或空结果改述成成功。")

Coverage

What the index resolves and probes
Brands resolved
31,690
Brands on two or more hosts
7,655
Held for review
14,806 listings
Tools listed by probe
13,241 servers

Where are you listed?

Paste your MCP server, plugin or company URL to see your listings, tools and scan findings in one place.

Check my InvokeRank Scan a server