INITE MCP
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| INITE_TOKEN | No | Use this token instead of the stored one. | |
| INITE_MCP_URL | No | Point at a different endpoint. Default https://inite.ai/api/mcp. | https://inite.ai/api/mcp |
| INITE_AUTH_URL | No | Authorization server. Default https://auth-api.inite.ai. | https://auth-api.inite.ai |
| INITE_TOKEN_FILE | No | Where the token lives. Default ~/.config/inite/mcp.json. | ~/.config/inite/mcp.json |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_ai_accessA | Read a site's robots.txt and say which AI crawlers may fetch it, separating the ones that retrieve pages to answer live questions from the ones that only collect training data. Blocking the first kind is what makes a site invisible in AI answers; blocking the second costs nothing. Runs locally, no account needed. |
| check_identity_filesA | Probe a site for the identity files an AI engine may look for — llms.txt, ai.json, identity.json and the rest — and report which exist. Runs locally, no account needed. |
| check_page_signalsA | Read a site's homepage and report the signals an engine uses to work out what it is: title, description, canonical, hreflang and the Schema.org types in its JSON-LD. Runs locally, no account needed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 3 tools
Each tool targets a distinct aspect of site visibility: AI crawler access, identity files, and page signals. There is no functional overlap, so an agent can reliably select the right tool.
All tools follow the same check_<object> pattern, making the set highly predictable. Naming is uniform and reflects a clear verb-noun convention.
Three tools is a tight, focused set for a site analysis server. Each tool covers a distinct checking task and none feel redundant or out of scope.
The tools cover the main signals for AI visibility: robots.txt, identity files, and homepage metadata. A minor gap is the lack of a combined summary or deeper content analysis, but the core read-only audit workflow is well covered.