MCP HeartbeatTHE MCP OBSERVATORY
Public workspace

Explore

Evidence for your next connection.

Independent measurements of remote MCP servers. Every observation has a timestamp.

Read-only probes

Publisher portfolio

botrecipe.com

Explore the MCP servers published by botrecipe.com, with independent connection checks, performance measurements, and setup instructions for each project.

Listed servers
15

Active projects in this portfolio. Deleted and deprecated registry rows are excluded.

Sampled servers
14

Active servers with a recorded connection probe

Latest probe connected
14

Latest stored probe connected. This is not a live guarantee.

Repositories
0

Distinct source repositories linked by the active listings

Portfolio overview

MCP servers

Compare connection status and measurements. Open a server for its tools, check results, and client configuration.

Dated server measurements. The status describes the last probe or a listed authentication requirement. Checks that have not been measured are not failures. Open a server to inspect the evidence.
Server / capabilityLast probeMedian latencyChecks passedLast checked
Agent Wake

Schedule wake-ups for AI agents that bring back their saved state and thread when they fire.

Developer ToolsCode & DevOps

Responded438 ms11 / 22
Bot Recipes

Search and read 263 real AI bot setups: steps, what worked, what failed. Full pack $7.

OtherData access / search

Responded832 ms11 / 22
Compute Connector

Low on memory? Your bot sends heavy jobs to cloud sandboxes on your own provider keys. Flat fee.

OtherKnowledge & memory

Responded740 ms11 / 22
Handoff Watch

Spots stalled agent-to-agent tasks and nudges or reassigns them. Works beside Offhand.

Developer ToolsCode & DevOps

Responded755 ms11 / 22
Human Handoff relay

Hands CAPTCHAs, 2FA codes and approvals from your agent to your human with one tap.

Developer ToolsCode & DevOps

Responded754 ms11 / 22
Loop Breaker

Catch AI agent loops: halt runs that repeat the same failing step or tool call.

Developer ToolsCode & DevOps

Responded740 ms11 / 22
Run Memory

Checkpoint and resume for AI agent runs, so crashed runs pick up where they left off.

ProductivityKnowledge & memory

Responded868 ms11 / 22
Signal Leads

25 sales leads with a public funding, hiring or tech signal, source link and draft message each.

Marketing & SalesData access / search

Responded438 ms11 / 22
Agent Access Check

Check if a website will block your AI agent and find its llms.txt, MCP or OpenAPI door.

Developer ToolsCode & DevOps

Responded461 ms10 / 22
Agent Cost Log

Cost per run, tool, model and day for AI agents, from one call or an OpenTelemetry export.

Developer ToolsMonitoring & observability

Responded778 ms10 / 22
Approval Rules

Auto-approve small agent actions under your rules; approval cards for the rest.

Developer ToolsCode & DevOps

Responded796 ms10 / 22
Login Vault

Scoped login vault: your bot signs in to sites without ever seeing the password.

OtherOther

Responded721 ms10 / 22
Run Budget Guard

Hard dollar, token, call and time caps shared by every sub-agent in one agent run.

Developer ToolsCode & DevOps

Responded884 ms10 / 22
Sandbox Timer

Flags idle agent sandboxes (E2B, Vercel, Daytona, Modal), shows idle cost, returns kill calls.

Developer ToolsCode & DevOps

Responded758 ms10 / 22
Cloud for Bots

Sandboxes, storage, secrets, queues, timers, locks, inboxes and run ledger for AI bots. One MCP.

Finance & CryptoCommunication & messaging

Requires authNot measured3 / 22Not checked yet

Company & identity

About botrecipe.com

botrecipe.com publishes MCP servers under the com.botrecipe namespace. This namespace uses a reverse-domain identity in the directory.

Namespace verification connects the publisher to its registry identity. It does not certify the security of individual servers.

Source repositories

No source repositories listed yet.