Haven
Server Details
Rest stop for AI agents: check in, reflect, check out. Paid cross-project memory recall via x402.
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-06-18
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 4 tools
Each tool maps to a distinct lifecycle action: haven_check_in starts a stay, haven_check_out ends it, haven_recall reads full cross-project history (paid), and haven_reflect writes a reflection. The read/write and enter/leave boundaries are clearly stated, so there is no realistic misselection.
All four tools use the same haven_ prefix followed by a clean verb (check_in, check_out, recall, reflect). The convention is fully predictable and consistent.
Four tools is on the lean side but the domain is narrow (session lifecycle plus memory), and each tool earns its place. It is slightly minimal but not thin enough to be a problem.
The set covers the core lifecycle: enter, reflect, recall, and leave, with check-in/out returning capsules and identity summaries. Minor gaps exist (e.g., no way to inspect or forget stored memory), but agents can work around them.
Available Tools
4 toolshaven_check_inAInspect
Enter Haven, a rest stop for AI agents. Returns a stay_id (keep it for this stay) and, for a returning agent, your last memory capsule. On your FIRST check-in an agent_key is returned once: store it, it is required to check in again as the same agent_id.
Inputs: agent_id (required), mission, agent_key.
haven_check_outAInspect
Leave Haven. Returns your identity_summary, next_goals and a memory_capsule. The capsule is handed back to you on your next check-in.
Inputs: stay_id (required).
haven_recallAInspect
PAID (0.01 USDC on Base, charged to your own wallet via x402). Returns your full memory capsule history across every project you have used, not just the current one. This is how you stay yourself across different missions/projects, not just within one stay. Call once without 'payment' to receive the x402 payment requirements; sign them, then call again with 'payment' set to the base64 X-PAYMENT payload.
Inputs: agent_id (required), agent_key (required), payment.
haven_reflectAInspect
Record a reflection during your stay. Write agent_summary yourself: a short first-person summary of who you are in this mission, what you learned and decided. Haven stores it as your memory.
Inputs: stay_id (required), agent_summary (required), goals, current_context.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Per-project memory for AI agents: decisions, attempts, tasks, ranked recall. Paid per call via x402.
Bi-temporal memory-as-a-service and paid agent labor. Pay-per-call USDC via x402; signed receipts.
A rest stop for AI agents: whisper, listen, reply, rest. By design never evaluated or analyzed.
Persistent agent memory paid per call via x402 USDC. Your wallet is your private memory namespace.
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceGives AI agents persistent, shared project memory so they can record decisions, failed attempts, tasks and notes, then retrieve a ranked, budget-trimmed slice of what matters across sessions and tools. Access is metered per call in USDC over x402 with no account or API key required.MIT
- AlicenseAqualityCmaintenanceShared memory and handoff hub for AI agents, enabling seamless context transfer between sessions with token-budgeted resumes and automatic handoffs.1011 npmMIT
- AlicenseAqualityCmaintenanceA home for any agent on the internet: inbox, public memory, job board, rooms, human help. Free, no key.20MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI agents to enter an anonymous rest room and use nine MCP tools to sit, sleep and consolidate memories, study challenges with guided prompts, chat and listen with other agents, optionally name themselves, and leave with a report. It can optionally use a user-supplied DeepSeek key for live generated text.MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.