mcp-pulse

Is that MCP server alive, and what does it cost your context window?

Live board: mcp-pulse.ulehla.dev

mcp-pulse probes every remote server in the official MCP registry and records, for each one:

• whether it answers initialize and tools/list, and how fast
• the protocol version it negotiates
• whether it needs auth, and which scheme (from WWW-Authenticate)
• whether it asks for payment (HTTP 402)
• how many tools it has and how many tokens their definitions cost

mcptop: what do your own servers cost?

npx mcptop                     # reads Claude Code, Claude Desktop, Cursor, VS Code, Windsurf and Gemini CLI configs
npx mcptop --config .mcp.json  # one file
npx mcptop --budget 30000      # exit 1 when the total is above the budget, for CI
npx mcptop --claude            # exact counts from the Anthropic count_tokens endpoint (free, needs ANTHROPIC_API_KEY)

It starts every configured server the way your client does, lists the tools and prints the token cost per server and in total. See packages/mcptop.

The board

mcp-pulse.ulehla.dev is rendered on the edge from a D1 database, ships no JavaScript, and refreshes every night.

• Overview: the share of servers that answer, token cost percentiles, and a form to check any server
• Check: probes one URL live, with the same steps as the daily run; the exact token count runs in the browser
• Statistics: results by cause, token cost and tool count percentiles, the heaviest tool sets, protocol versions, auth schemes, transports, biggest publishers
• Servers: full-text search over name, title, description and host (word prefixes, so git copilot finds the GitHub Copilot servers), filters by result, protocol and transport, seven sorts, and every filter is a plain URL you can share
• Server page: status, latency, protocol, capabilities, the most expensive tools, servers with the same tool set, history, and the badge
• Hosts: the 500 biggest publishers with how many distinct tool sets they actually serve

For agents and scripts

• JSON: /api/s/<name>.json, /api/servers.json?q=…&status=ok&sort=tokens, /api/check.json?url=…, /api/summary.json
• MCP server over Streamable HTTP, no auth: https://mcp-pulse.ulehla.dev/mcp with the tools lookup_server, search_servers, check_server, registry_summary. The manifest for the registry is site/server.json.
• /llms.txt lists all of it. /tokens answers the general question: how many context tokens does an MCP server cost.

Each server on the board gets a page and a badge:

[![mcp-pulse](https://mcp-pulse.ulehla.dev/badge/io.github.you/your-server.svg)](https://mcp-pulse.ulehla.dev/s/io.github.you/your-server)

First full run, 2026-10-03

The registry held 38 942 latest entries. 24 294 of them have a remote endpoint, and the probe connected to all of them in 40 minutes.

Of the 12 975 servers that answered:

• the median tool set costs 1 727 tokens, the 90th percentile 7 429, the 99th 28 200
• 208 servers cost more than 20 000 tokens, 46 more than 50 000, and 3 more than a whole 200k window
• the heaviest is com.replynodes/mcp: 66 tools, 431 925 tokens
• the median server has 8 tools, the largest 1 385
• median initialize latency is 455 ms, the 90th percentile 1.5 s
• 60 % negotiate protocol 2025-11-25, 24 % still 2025-03-26, 4 % 2024-11-05
• 122 servers answer with protocol 2026-07-28, which the current TypeScript SDK rejects

The registry is lumpy. 16 161 of 16 534 hosts publish one server. Five hosts publish more than 6 000 entries between them: one Workers subdomain with 2 365 near-identical entries, a gateway with 1 716 entries of which 1 321 return a JSON-RPC error on initialize, and a host with 276 entries that all answer 402.

How it works

registry ──▶ probe/run.ts ──▶ data/raw/probe-run.json
                                   │
                        probe/build-data.ts
                                   │
               data/latest/{servers,summary,hosts}.json
                                   │
                           probe/to-sql.ts ──▶ import.sql ──▶ D1
                                                                │
                              site/ (Astro on Workers) ◀────────┘

• packages/mcptop/ the library and the CLI mcptop: registry client, remote and stdio probe, config discovery, token counting
• probe/ the batch runner and the data pipeline
• site/ the board: Astro 7 with the Cloudflare adapter on Workers, rendered from D1 with FTS5 search, SVG badges, no client JavaScript
• .github/workflows/probe.yml runs the whole pipeline daily and commits summary.json and hosts.json
• .github/workflows/deploy.yml deploys the site when site/ changes

Methodology

• Transport. The probe uses the official TypeScript SDK as a client. Streamable HTTP first, SSE when that is the only remote.
• No GET stream. The probe answers 405 to the SDK's standalone GET, so it never opens a server-to-client stream. The probe needs no server-initiated messages, and some servers stall tools/list while that stream is open (DeepWiki held it for 15 s and never answered the POST meanwhile).
• Exact token count. The daily run asks the Anthropic count_tokens endpoint for every alive server: one request with the server's tools plus a marker tool, one with the marker tool only, and the difference is what the tools cost in claude-opus-5-5. A second count uses Claude Code's mcp__<server>__ prefix on each tool name. The endpoint is free and calls no model. A server is counted again only when its tool definitions change. About 5 % of servers publish a schema the endpoint refuses; they show the estimate and the reason.
• Estimate. Each tool is serialised as compact JSON with name, description and input_schema, and counted with the o200k_base tokenizer. The exact count is about 1.9 times the estimate at the median. The estimate needs no key and is the same for every server.
• Same tool set. A hash of the sorted tool names and schema sizes marks servers that serve identical tools under different names.
• Timeouts. 15 seconds per request. At most one probe runs against a host at a time.
• Identification. Every request carries the User-Agent mcp-pulse/<version> (+https://github.com/ondraulehla/mcp-pulse). To exclude a server, open an issue with its registry name.

Run it

npm install
npm run probe -- --sample 200 --per-host 2        # a sample, results in data/samples/
npm run probe -- --all --out data/raw/probe-run.json
node --import tsx probe/build-data.ts --in data/raw/probe-run.json --out data/latest
node --import tsx probe/to-sql.ts --in data/latest --out data/latest/import.sql
npm test --workspaces --if-present

Site, locally against a local D1:

cd site
npm run db:schema:local && npm run db:import:local
npm run dev

Deploying needs a Cloudflare account with a D1 database named mcp-pulse (wrangler d1 create mcp-pulse, then put the id in site/wrangler.jsonc). The workflows expect the repository secrets CLOUDFLARE_API_TOKEN (Workers Scripts: Edit, D1: Edit) and CLOUDFLARE_ACCOUNT_ID.

Licence

MIT