mcp-registry/md.install/try · v1.0.0
As of 2026-10-26 18:41 UTC, the Install Try MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Create guides as MCP servers to instruct coding agents to use your software (library, API, etc).
Point your MCP client at this streamable-http endpoint: https://install.md/mcp/try
13 of 13 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 →
7 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 →
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%2Fmd.install%2Ftry/fixes
{
"name": "add_data_source",
"description": "Add a new data source to a project",
"inputSchema": {
"type": "object",
"required": [
"session_id",
"project_slug",
"url",
"type"
],
"properties": {
"url": {
"type": "string",
"description": "The URL of the data source"
},
"type": {
"enum": [
"web_crawl",
"git_clone",
"resource_load"
],
"type": "string",
"description": "The type of data source"
},
"session_id": {
"type": "string",
"description": "The anonymous session ID"
},
"project_slug": {
"type": "string",
"description": "The slug of the project to add the data source to"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "add_tool",
"description": "Add a new tool/step to a project",
"inputSchema": {
"type": "object",
"required": [
"session_id",
"project_slug",
"name",
"display_name"
],
"properties": {
"name": {
"type": "string",
"description": "The unique name of the tool (used as identifier)"
},
"tool_type": {
"enum": [
"step",
"builtin",
"tip"
],
"type": "string",
"default": "step",
"description": "The type of tool (step, builtin, tip)"
},
"is_enabled": {
"type": "boolean",
"default": true,
"description": "Whether the tool is enabled"
},
"session_id": {
"type": "string",
"description": "The anonymous session ID"
},
"step_order": {
"type": "number",
"description": "The order of this step in the project workflow"
},
"description": {
"type": "string",
"description": "Description of what the tool does"
},
"tool_schema": {
"type": "string",
"description": "JSON schema for tool parameters"
},
"display_name": {
"type": "string",
"description": "The human-readable display name of the tool"
},
"project_slug": {
"type": "string",
"description": "The slug of the project to add the tool to"
},
"response_template": {
"type": "string",
"description": "Markdown template for tool response"
}
},
"additionalProperties": false
},
"annotations": {
"readOnlyHint": false,
"destructiveHint": false,
"idempotentHint": false
}
}{
"name": "create_project",
"description": "Create a new project in the anonymous session",
"inputSchema": {
"type": "object",
"required": [
"session_id",
"name",
"slug"
],
"properties": {
"name": {
"type": "string",
"description": "The display name of the project"
},
"slug": {
"type": "string",
"description": "The URL slug for the project (used in URLs)"
},
"is_public": {
"type": "boolean",
"default": false,
"description": "Whether the project is public or private"
},
"session_id": {
"type": "string",
"description": "The anonymous session ID"
},
"overview_content": {
"type": "string",
"default": "",
"description": "Markdown content for the project overview"
}
},
"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/md.install/try"],"email":"[email protected]"}'Agents: watch_tool({"toolId": "mcp-registry/md.install/try"}) over MCP.
add_tool ~313 tokensupdate_tool ~289 tokensupdate_project ~197 tokensreorder_steps ~192 tokenscreate_project ~180 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%2Fmd.install%2Ftry?ref=badge)
<a href="https://glimind.com/server/mcp-registry%2Fmd.install%2Ftry?ref=badge"><img src="https://glimind.com/v1/readiness/badge/mcp-registry%2Fmd.install%2Ftry.svg" alt="MCP agent-readiness"></a>
.. image:: https://glimind.com/v1/readiness/badge/mcp-registry%2Fmd.install%2Ftry.svg :target: https://glimind.com/server/mcp-registry%2Fmd.install%2Ftry?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 sha256:6c75c879ffc28eec…, first seen 2026-10-17, included at leaf 16833 of 74,788. Version history · verify what your client received.
Compare: most reliable data servers · most reliable other servers · most reliable productivity 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 18:41 UTC, the Install Try MCP server is up with a Glimind reliability score of 100/100 (grade A). Over the last 30 days it answered 100% of Glimind's liveness checks.
Install Try MCP server advertises 13 tools, including add_data_source, add_tool, create_project, create_session, delete_data_source.
Point your MCP client at this streamable-http endpoint: https://install.md/mcp/try
Glimind scanned all 13 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.