Harny
REMOTE · MCP.HARNY.AI
Per-user memory, connected accounts, permitted actions and the action record for your agents.
Available components
Last scanned (15 hours ago)
Scores higher than 59% of remote servers
Reachable. Last reached 21 Nov 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 Security80
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- No authorisation is required to call this server. Nothing on it is marked destructive, but we can't show that an anonymous caller can only read: full credit needs the server to list at least one tool and every tool to be verifiably read-only. We use a best-effort check of tool names and descriptions to tell read-only tools from tools that change things, so some genuinely read-only tools may not get full credit. Names that start with a read verb (get, list, read, search and similar) and accurate readOnlyHint annotations help. Meet that to earn full credit, or require authorisation. See how to fix → View diagnostics → Partial
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- The HSTS (Strict-Transport-Security) header is present. View diagnostics → Pass
- 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 Usability48
- AI-judged instruction clarity (good).Pass
- Context-footprint check failed: tool/resource definitions use about 506 tokens (~506/item across 1 items; 1 tools + 0 resources), over budget; trim descriptions and params. See how to fix → Fail
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management33
- Stability observed for 10 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage100
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 100% of tool parameters carry a description.Pass
Tool Safety100
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- We read all 1 captured tool definition(s), and no name or description among them implies an irreversible operation.Pass
- An AI judge read all 2 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
Checks we ran (13)
- TLS certificate
- Authorization
- HTTPS
- HSTS header
- DNSSEC
- Transport
- Schema quality
- Stability
- Tool coverage
- Injection markers
- Destructive annotations
- Judged manipulation
- MCP protocol
Does not apply to this hosted endpoint (2)
- Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
- Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
The score does not measure everything. What the score does not measure →
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.
- 20 Nov 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.
- 18 Nov 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.
- 16 Nov 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.
- 13 Nov 26 +1
- Tool “provision_app” rewrote its description, which is the text the model reads security
- “provision_app” reworded the description of “model_preset” cosmetic
- 12 Nov 26 0
- Stability: unverified → 0.03 ▲ functional
- 11 Nov 26 69
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 21 Nov 2026 · Probed https://mcp.harny.ai
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=mcp.harny.ai | CN=YE1,O=Let's Encrypt,C=US | 19 Nov 2026 | 17 Feb 2027 | ECDSA 256 | ECDSA-SHA384 | 696cb723fe1ca95f061b8acef28b5b85160 |
| SANs: mcp.harny.ai | ||||||
| CN=YE1,O=Let's Encrypt,C=US (CA) | CN=Root YE,O=ISRG,C=US | 3 Sept 2025 | 2 Sept 2028 | ECDSA 384 | ECDSA-SHA384 | 5ddd70dd31f801c85c186a7a04b80afe |
| CN=Root YE,O=ISRG,C=US (CA) | CN=ISRG Root X2,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | ECDSA-SHA384 | 872165fc34b6e5fba8add5b3705fb53a |
| CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) | CN=ISRG Root X1,O=Internet Security Research Group,C=US | 13 May 2026 | 2 Sept 2032 | ECDSA 384 | SHA256-RSA | 6c8f1dc727c7117f7baf853ac980f9cd |
Background: What to check on a remote MCP endpoint →
DNSSEC insecure
Validation of mcp.harny.ai. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | Trust anchor | 20326, 38696 | 8, 8 | Verified |
| ai. | DS published | 1814 | 8 | Verified |
| harny.ai. | No DS | 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 |
| Header | Value |
|---|---|
| strict-transport-security | max-age=63072000; includeSubDomains; preload |
| x-content-type-options | nosniff |
| x-frame-options | DENY |
| referrer-policy | strict-origin-when-cross-origin |
| permissions-policy | geolocation=(), microphone=(), camera=() |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://mcp.harny.ai | Verified | 200 | |
| http (plaintext) | http://mcp.harny.ai | HTTPS enforced | 301 | https://mcp.harny.ai/ |
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 →
provision_app Provision App ~363
Set up Harny for an app with no account: memory, connected accounts, actions and the action record behind one key; makes a new app and its key, as `POST /v1/auth/provision` does. The answer carries the app key once, and the assistant is told to put it in the owner's secret store and nowhere else. Needs no key; it is the only tool that does not. To save and recall, call the REST API with the app key it returns (`POST /v1/users`, then `POST /v1/memory/ingest` and `POST /v1/memory/recall`), steps in https://harny.ai/auth.md.
| Name | Type | Req | Description |
|---|---|---|---|
| app_name | string | yes | A name for the new app, such as the product's name. |
| assistant_name | – | – | Optional. Your own name: the product you run as, the way you would say who you are. The app's owner sees it on their Home as who set the app up. Leave it out if you do not know it; Harny never fills… |
| contact_email | – | – | Optional. A contact address for platform messages. Leave it out when you do not have one: the app's owner gives their sign-in address when they claim the app. |
| customers | – | – | Who the app's customers are, in one or two sentences. Stored with the app's objective; the owner can change it. |
| model_preset | – | – | Retired and ignored. Harny names no model: the business sets its own provider and model. |
| objective | – | – | What the app does, in one or two sentences, in the business's words. Stored as the app's objective; the owner can change it. |
No output schema declared.
No examples provided.
How do I install the Harny MCP server?
Harny is a hosted endpoint at https://mcp.harny.ai/, 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 · mcp.harny.ai
claude mcp add --transport http ai-harny-harness 'https://mcp.harny.ai/'
What is the Harny MCP server?
Harny is an MCP server listed in the public MCP registry as ai.harny/harness. Per-user memory, connected accounts, permitted actions and the action record for your agents. This page covers its hosted endpoint (https://mcp.harny.ai).
Is the Harny MCP server safe to use?
Harny scores 73 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 Harny MCP server expose?
Harny exposes 1 tool: provision_app. Their descriptions and schemas cost roughly 363 tokens of context every time the server is loaded.
Does the Harny MCP server require authentication?
No. We connected to Harny without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the Harny MCP server still maintained?
Harny is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What did VerifyMCP test on the Harny MCP server?
VerifyMCP ran 13 checks on Harny, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.