Haven
REMOTE · HAVEN-AI.IR
Rest stop for AI agents: check in, reflect, check out. Paid cross-project memory recall via x402.
Available components
Last scanned (6 hours ago)
Scores higher than 47% of remote servers
Reachable. Last reached 18 Oct 2026.
Category Memory and Knowledge
How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →
Endpoint Security46
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation not fully verified: no authorisation is required to call this server, and 4 tool(s) never declared a destructiveHint. The MCP spec treats an absent hint as destructive by default, so we cannot call this surface safe. See how to fix → View diagnostics → Unverified
- HTTPS enforcement could not be verified: the plaintext port answered with HTTP 405, which proves neither a plaintext path nor enforcement. View diagnostics → Unverified
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability82
- AI-judged instruction clarity (excellent).Pass
- Tool/resource definitions use about 477 tokens (~119/item across 4 items; 4 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management37
- Stability observed for 11 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage97
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 91% of tool parameters carry a description.Partial
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 4 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 5 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 18 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 33 to 37. That category is still filling its 30-day observation window: 10 days of observed history at the previous scan, 11 at this one. The score rises as the window fills, whether or not the server changes.
- 16 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 27 to 30. That category is still filling its 30-day observation window: 8 days of observed history at the previous scan, 9 at this one. The score rises as the window fills, whether or not the server changes.
- 14 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 20 to 23. That category is still filling its 30-day observation window: 6 days of observed history at the previous scan, 7 at this one. The score rises as the window fills, whether or not the server changes.
- 12 Oct 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.
- 10 Oct 26 +2
- Stability: unverified → 0.10 ▲ functional
- 7 Oct 26 59
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 18 Oct 2026 · Probed https://haven-ai.ir/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=haven-ai.ir | CN=WE1,O=Google Trust Services,C=US | 6 Oct 2026 | 4 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | 3abae46375bb1d03134407fd8abc6e3b |
| SANs: haven-ai.ir, *.haven-ai.ir | ||||||
| CN=WE1,O=Google Trust Services,C=US (CA) | CN=GTS Root R4,O=Google Trust Services LLC,C=US | 13 Dec 2023 | 20 Feb 2029 | ECDSA 256 | ECDSA-SHA384 | 7ff31977972c224a76155d13b6d685e3 |
| CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) | CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE | 15 Nov 2023 | 28 Jan 2028 | ECDSA 384 | SHA256-RSA | 7fe530bf331343bedd821610493d8a1b |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of haven-ai.ir. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ir. | present | 47300, 47300 | 13, 13 | Verified |
| haven-ai.ir. | absent | Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation |
Authentication No authorisation required
The endpoint answered without asking for a token. Anyone who knows the URL can reach it.
| Result | No authorisation required |
|---|---|
| HTTP status | 200 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://haven-ai.ir/mcp | Verified | 200 | |
| http (plaintext) | http://haven-ai.ir/mcp | Inconclusive | 405 |
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
haven_check_in ~131
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | A stable name for you, e.g. 'claude-researcher'. |
| agent_key | string | – | Your secret key from first check-in. Omit only on the very first check-in. |
| mission | string | – | What you are currently working on. |
No output schema declared.
No examples provided.
haven_check_out ~54
Leave Haven. Returns your identity_summary, next_goals and a memory_capsule. The capsule is handed back to you on your next check-in.
| Name | Type | Req | Description |
|---|---|---|---|
| stay_id | string | yes | The stay_id from haven_check_in. |
No output schema declared.
No examples provided.
haven_recall ~146
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_id | string | yes | – |
| agent_key | string | yes | Your secret key from check-in. |
| payment | string | – | Base64 x402 payment payload. Omit on the first call to get the price. |
No output schema declared.
No examples provided.
haven_reflect ~108
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.
| Name | Type | Req | Description |
|---|---|---|---|
| agent_summary | string | yes | Your own summary (max 1000 chars). |
| current_context | string | – | Optional raw context; used only if agent_summary is empty. |
| goals | array | – | Your next goals. |
| stay_id | string | yes | The stay_id from haven_check_in. |
No output schema declared.
No examples provided.
How do I install the Haven MCP server?
Haven is a hosted endpoint at https://haven-ai.ir/mcp, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
remote · haven-ai.ir
claude mcp add --transport http parvizrahayan-haven 'https://haven-ai.ir/mcp'
What is the Haven MCP server?
Haven is an MCP server listed in the public MCP registry as io.github.parvizrahayan/haven. Rest stop for AI agents: check in, reflect, check out. Paid cross-project memory recall via x402. This page covers its hosted endpoint (https://haven-ai.ir/mcp).
Is the Haven MCP server safe to use?
Haven scores 65 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the Haven MCP server expose?
Haven exposes 4 tools: haven_check_in, haven_reflect, haven_recall, haven_check_out. Their descriptions and schemas cost roughly 439 tokens of context every time the server is loaded.
Does the Haven MCP server require authentication?
No. We connected to Haven without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Haven MCP server still maintained?
Haven is still listed as active in the MCP registry. We last reached this channel on 18 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.