mcp-registry/dev.harvis/harvis · v1.0.0
As of 2026-10-26 23:37 UTC, the Harvis MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Deploy static sites from AI agents: deploy_site publishes files and returns a live URL in seconds.
Point your MCP client at this streamable-http endpoint: https://harvis.dev/api/mcp
1 tool(s) look like they change state (create/send/delete/pay…) but declare no destructiveHint.
Set annotations {"readOnlyHint": false, "destructiveHint": true|false, "idempotentHint": …}. Clients use these to ask the user before a side effect and to auto-approve safe reads. How to fix →
1 of 1 tool(s) carry no readOnlyHint/destructiveHint annotations.
Annotate read-only tools with {"readOnlyHint": true}. Agents and gateways can then run them without a confirmation prompt, and route around destructive ones. How to fix →
Handshake + tools/list takes ~2,036 ms.
Serve tools/list from memory, keep the process warm, and host close to your users. Every new agent session pays this before its first call.
No tool declares an outputSchema.
Declare outputSchema and return structuredContent (MCP 2025-06-18+). Agents can then parse results without guessing, and chain tools reliably. How to fix →
Paste-ready definitions with the problems above fixed. Changes marked verify need a human look. All of them as JSON: /v1/readiness/mcp-registry%2Fdev.harvis%2Fharvis/fixes
{
"name": "deploy_site",
"description": "Publish a static website to harvis.dev and get a live public URL back instantly. No account or authentication is needed. Pass every file of the site (HTML, CSS, JS, images...) with its path relative to the site root; include an index.html. Returns the live site 'url' plus a private 'claimUrl' — always show the user BOTH links and tell them to open claimUrl and sign in (free) to attach the site to their account so they can edit or delete it later. Warn them claimUrl is private and cannot be recov",
"inputSchema": {
"type": "object",
"$schema": "http://json-schema.org/draft-07/schema#",
"required": [
"files"
],
"properties": {
"name": {
"type": "string",
"maxLength": 120,
"description": "Optional human-friendly site name."
},
"files": {
"type": "array",
"items": {
"type": "object",
"required": [
"path",
"content"
],
"properties": {
"path": {
"type": "string",
"description": "Path relative to the site root, using forward slashes, e.g. \"index.html\" or \"css/style.css\"."
},
"content": {
"type": "string",
"description": "The file's content: UTF-8 text by default, or base64 when encoding is 'base64'."
},
"encoding": {
"enum": [
"text",
"base64"
],
"type": "string",
"description": "Defaults to 'text'. Use 'base64' for binary files like images."
}
},
"additionalProperties": false
},
"maxItems": 500,
"minItems": 1,
"description": "Every file of the site. Total size limit: 50 MB."
},
"subdomain": {
"type": "string",
"description": "To UPDATE an existing site instead of creating a new one: the site's subdomain from an earlier deploy. Requires deployToken."
},
"deployToken": {
"type": "string",
"description": "The site's private deploy token returned by the deploy that created it (also shown in the dashboard). Requires subdomain."
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}Get an email or webhook when this server's readiness drops by 10+ points, tool-poisoning text appears, or a tool breaks:
curl -X POST https://glimind.com/v1/subscriptions -H 'content-type: application/json' -d '{"tools":["mcp-registry/dev.harvis/harvis"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/dev.harvis/harvis"}) over MCP.
deploy_site ~482 tokensStatic checks of the advertised tools/list (schema, descriptions, annotations, tool-poisoning patterns, names, size) plus observed protocol, uptime, latency and contract changes. Read-only: no tool is ever called. Weights: schema 15, docs 20, safety 15, efficiency 15, compatibility 15, protocol 5, reliability 10, stability 5. Token counts are estimates (~3.6 characters per token).
Operator? Fix these, then re-check live. Embed the readiness badge:
[](https://glimind.com/server/mcp-registry%2Fdev.harvis%2Fharvis?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fdev.harvis%2Fharvis?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.harvis%2Fharvis.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fdev.harvis%2Fharvis.svg :target: https://glimind.com/server/mcp-registry%2Fdev.harvis%2Fharvis?ref=badge :alt: MCP agent-readiness
Glimind records every version of this server's tool definitions in a signed, append-only transparency log. Current manifest sha256:ec91dd7de8d54869…, first seen 2026-10-17, included at leaf 10409 of 76,123. Version history · verify what your client received.
Compare: most reliable web servers
Glimind tells agents whether a server is up right now and how to call it, then fails over to a live alternative when it isn't.
Claude Code
claude mcp add --transport http glimind https://glimind.com/mcp
Claude Desktop · Windsurf · Cline (mcpServers JSON)
{
"mcpServers": {
"glimind": {
"type": "http",
"url": "https://glimind.com/mcp"
}
}
}
As of 2026-10-26 23:37 UTC, the Harvis MCP server is up with a Glimind reliability score of 98/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Harvis MCP server advertises 1 tool, including deploy_site.
Point your MCP client at this streamable-http endpoint: https://harvis.dev/api/mcp
Glimind scanned all 1 tool definitions for tool-poisoning patterns — hidden or invisible characters, instructions that override the model, concealment from the user, requests to read credential or MCP config files, conversation exfiltration and cross-tool shadowing — and found none. This checks what the server tells the model, not what its code does; review the source before granting access to sensitive data.
Status page: 90-day uptime, every outage and how long it lasted.
Claim this listing to get the Verified operator marker, a remediation checklist and owner analytics, or embed the live badge from any of the tool pages above. Maintainers: alerts, deploy attestation and monthly reports.
Status is an automated estimate from Glimind's liveness checks (handshake and tool listing only; no tool is ever called) and may lag or differ from your network. Glimind is not affiliated with this server or its operator. Operator? Request a correction or opt out at https://glimind.com/opt-out.