Agent Daily MCP server
Commit Oct 26, 2026Monitors the real-time reliability and latency of 65 agent APIs and MCP servers to help builders select healthy tool providers.
Also known as gregpunch/agent-daily, agent-daily
- Stars
- 0
- Tools
- 4
- Downloads, 30 days
- —
- Latest version
- 0.3.0
- Last commit
- Oct 26, 2026
- License
- —
What is Agent Daily MCP?
Agent Daily monitors the real-time reliability and latency of 65 agent APIs and MCP servers to help builders select healthy tool providers. It exposes 4 tools, such as recommend, incidents, list_tools.
Summary generated from the project's README
About Agent Daily MCP server
Agent Daily provides a real-time reliability index for 65 different APIs and MCP servers used by AI agents. It tracks uptime, latency, and incident history for various categories including LLMs, search, scraping, email, and vector databases. Developers can use this data to verify if a tool is functional before making a call, allowing them to implement fallback logic and avoid unnecessary retries during outages.
The service is available as a remote MCP server via a Cloudflare Worker endpoint that requires no API keys or authentication. It offers specific tools like list_tools, tool_status, recommend, and incidents to help builders make informed decisions. For those monitoring LLM performance, it includes a live probe that tracks model correctness and speed. The data is refreshed hourly and focuses on reachability through HTTP status checks from a single probe location.
What you can do with it
- 1Select healthy tool providersAn AI developer can ask the client to find the most reliable provider for a specific task like sending an email.
- 2Implement automated fallback logicA developer can program an agent to switch to a different provider if the primary tool shows a critical vendor status.
- 3Analyze historical service reliabilityA builder can review the past week of uptime and latency metrics for a specific API to assess its stability.
Written from the project's README. Every use case is checked against a quote from it.
How to install Agent Daily MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall Agent Daily MCP in Claude Code
$ claude mcp add --transport http agent-daily https://agent-daily.agentdaily.workers.dev/mcpInstall Agent Daily MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"agent-daily": {
"url": "https://agent-daily.agentdaily.workers.dev/mcp"
}
}
}Install Agent Daily MCP in VS Code
.vscode/mcp.json
{
"servers": {
"agent-daily": {
"type": "http",
"url": "https://agent-daily.agentdaily.workers.dev/mcp"
}
}
}Install Agent Daily MCP in VS Code CLI
$ code --add-mcp '{"name":"agent-daily","type":"http","url":"https://agent-daily.agentdaily.workers.dev/mcp"}'Install Agent Daily MCP in Codex
$ codex mcp add agent-daily --url https://agent-daily.agentdaily.workers.dev/mcpInstall Agent Daily MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.agent-daily] url = "https://agent-daily.agentdaily.workers.dev/mcp"
Install Agent Daily MCP in Gemini CLI
$ gemini mcp add -s user --transport http agent-daily https://agent-daily.agentdaily.workers.dev/mcpInstall Agent Daily MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"agent-daily": {
"url": "https://agent-daily.agentdaily.workers.dev/mcp",
"type": "http"
}
}
}Agent Daily MCP tools 4
Detected from the READMErecommendincidentslist_toolstool_status
| recommend | — | |
| incidents | — | |
| list_tools | — | |
| tool_status | — |
Automated checks
Ran Nov 14, 2026Full report →Not verified yet. A server needs a score of 80, no serious finding, and enough data for us to check. How checks work · What to fix for more points
- Source repository linked and reachablegregpunch/agent-daily is public and reachablegithub.com/gregpunch/agent-daily ↗Pass
- Package names this repository as its sourceNot checked
- Build provenance (Sigstore attestation)Not checked
- Open source license (OSI)No licenseFinding
- Commit or release in the last yearLast commit or release 2026-10-26github.com/gregpunch/agent-daily ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNot checked
- No critical advisory in the package or its dependenciesNot checked
- No hidden instructions to the model4 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNo tool named like delete, drop or execPass
- Remote endpoint answers the MCP handshakeinitialize answered with protocol 2025-06-18 in 56 msPass
README
View on GitHubAgent Daily: is this tool up right now?
A free, hourly reliability index for the APIs and MCP servers AI agents call: 65 providers across LLMs, search, scraping, email, vector DBs, voice, payments, messaging, maps, CRM, storage and public remote MCP servers, with 7-day uptime, p50/p95 latency and incident history.
Built for agent builders. Check before your agent calls a tool, fall back when a tool is down, and stop burning retries on outages.
- Status page: https://gregpunch.github.io/agent-daily/
- Machine-readable: https://gregpunch.github.io/agent-daily/status.json
- Agent guide: https://gregpunch.github.io/agent-daily/llms.txt
- MCP server (no key): https://agent-daily.agentdaily.workers.dev/mcp, with tools
list_tools,tool_status
claude mcp add --transport http agent-daily https://agent-daily.agentdaily.workers.dev/mcp
Consume status.json
import requests
s = requests.get("https://gregpunch.github.io/agent-daily/status.json", timeout=5).json()
tool = next(t for t in s["tools"] if t["name"] == "OpenAI API")
if not tool["up"] or tool["vendor_status"] in ("major", "critical"):
... # route to a fallback provider
Fields: schema_version, generated_at (UTC), summary.{up,total}, and tools[] with name, category, up, http_status, latency_ms, vendor_status, uptime_24h_pct, checks_24h, error. Data is refreshed hourly; treat it as stale if older than about 2h. Please cache.
Limits: these are reachability checks only (an expected HTTP code), not correctness or quality tests. There is a single probe location.
A free public status page for 65 tools AI agents depend on. This is Phase 1, a two-week validation.
Run locally
python3 check.py # probe all tools -> results.db (SQLite)
python3 build.py # render site/index.html
Files: tools.json (config), tools.md (list + method), check.py, build.py, site/ (static output), preview.png.
Deploy plan (free tiers)
Recommended: GitHub Actions + GitHub Pages ($0).
- Push this folder to a public GitHub repo.
- Add
.github/workflows/check.ymlwithschedule: cron: "0 * * * *"(hourly). Steps: checkout,pip install requests,python check.py && python build.py, commitresults.dbback (or store it as an artifact), then deploysite/withactions/deploy-pages. - Turn on Pages (source: GitHub Actions). Public repos get unlimited Actions minutes.
Alternative: Cloudflare Worker cron + D1 + Pages ($0). Port check.py to a Worker scheduled() handler (free tier: 100k requests/day, cron triggers included). Store rows in D1 (free 5 GB), and render the page or serve JSON from the Worker or Pages. This option is the better base for the paid MCP/API later.
Estimated monthly cost
| Item | Cost |
|---|---|
| GitHub Actions + Pages (public repo) or Cloudflare free tier | $0 |
| Domain (optional, e.g. agentdaily.dev) | ~$1–1.25/mo ($12–15/yr) |
| Paid-API functional tests (Phase 2 only) | $0 now; cap $30–50 |
| Phase 1 total | $0–2/mo |
MCP server (mcp-worker/)
This is a stateless, read-only MCP server on a Cloudflare Worker. It uses Streamable HTTP at /mcp and offers two tools: list_tools(category?) and tool_status(name). Both read status.json with a 5-minute cache. It also serves /.well-known/mcp/server-card.json.
cd mcp-worker && npm install && npx wrangler dev # local
npm test # MCP SDK client check against localhost:8787
npx wrangler deploy # needs CLOUDFLARE_API_TOKEN + CLOUDFLARE_ACCOUNT_ID
MCP tools (v0.2.0)
Remote endpoint: https://agent-daily.agentdaily.workers.dev/mcp (Streamable HTTP, no auth, read-only)
recommend(task): maps a phrase or category ("send email", "web search", "llm", "scrape a page") to a category and returns the healthiest provider plus 1-2 fallbacks, with reasons and freshness.incidents(name?, days=7): outages and vendor incidents with UTC start/end.list_tools(category?): matches eithercategoryor routingtask.tool_status(name): full record, including 7-day uptime and p50/p95.
Data: status.json (current + 7d stats) and history.json (incidents), both regenerated hourly.
LLM Live Probe (v0.3.0)
- Leaderboard: https://gregpunch.github.io/agent-daily/llm/
- Methods: https://gregpunch.github.io/agent-daily/llm/methods.html
- JSON: https://gregpunch.github.io/agent-daily/llm/leaderboard.json
- MCP:
llm_leaderboard(sort?)at https://agent-daily.agentdaily.workers.dev/mcp
https://gregpunch.github.io/agent-daily/llm/: every 15 minutes ~20 popular models (via OpenRouter, plus optional direct OpenAI/Anthropic/Gemini control checks) get "Reply with exactly the word pong". Leaderboard (score = 60% 24h correctness + 40% speed), per-model detail pages and a methods page. Data: llm/leaderboard.json, llm/models/<id>.json. MCP tool: llm_leaderboard(sort?). Probing skips cleanly when no keys are set; spend is capped at $2.50/30 days in llm/models.json.
Agent Daily MCP questions
How do I add Agent Daily MCP to Claude Code?
Run claude mcp add --transport http agent-daily https://agent-daily.agentdaily.workers.dev/mcp in your terminal. Add --scope user to make it available in every project.
How do I add Agent Daily MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
What tools does Agent Daily MCP provide?
It exposes 4 tools, including recommend, incidents, list_tools, tool_status.
What kind of tools does Agent Daily monitor?
It monitors 65 providers including LLMs, search, scraping, email, vector DBs, voice, payments, messaging, maps, CRM, and storage.
How often is the status data updated?
The data is refreshed on an hourly basis.
Does the monitoring include correctness tests?
No, the service only performs reachability checks to ensure an expected HTTP code is returned.
Can I use the MCP server without an API key?
Yes, the MCP server is a stateless, read-only service that requires no authentication.