Content Tools

kitforai.com

Converts web pages to Markdown, manages knowledge bases of converted documents, and enables semantic search within them.

1 endpoint13 known toolsFirst detected July 26, 2026Last detected September 7, 2026

ENDPOINT 1

https://kitforai.com/api/mcp

No auth detected

MCP server metadata

Name: kit-for-ai
Version: 1.0.0

Capabilities

tools

Known tools 13

convert_url

Fetch a document or web page by URL and convert it to clean Markdown (or structured JSON).

Inferred read-only

list_recent_conversions

List the user's most recent conversions (id, file name, status).

Inferred read-only

list_knowledge_bases

List the user's knowledge bases (named knowledge bases of converted documents), with each knowledge base's id, name, kind, and document count.

Inferred read-only

read_knowledge_base

Read every document in a knowledge base as one combined Markdown document — use this to give the model access to all docs in a category.

Inferred read-only

search_knowledge_base

Semantically search a knowledge base and get back the most relevant chunks (ranked by score) instead of the whole knowledge base — use this for large knowledge bases or targeted questions.

Inferred read-only

write_knowledge_base

Write content back into a knowledge base as a versioned document — use this to save notes, memories, or generated content the user can review and revert.

Potential side effects

append_knowledge_base

Append content to a knowledge base — adds a new versioned document with the given content (searchable like any other doc).

Inferred read-only

edit_knowledge_base

Correct an existing document in a knowledge base by replacing a specific piece of text — use this for targeted fixes instead of rewriting the whole document.

Inferred read-only

remember

Save a fact, preference, or piece of context to the user's persistent memory.

Inferred read-only

remember_conversation

Extract and store the durable facts from a conversation transcript in ONE call — preferences, decisions, stable facts (transient chit-chat is dropped, near-duplicates skipped).

Inferred read-only

memory_profile

Get a compact synthesized profile of the user (or one end user) from their stored memories — who they are, preferences, projects, decisions in force.

Inferred read-only

recall

Search the user's persistent memory for relevant facts/context before answering.

Inferred read-only

crawl

Crawl a website (same-domain, bounded) and build a searchable knowledge base from it — then your agent can search_knowledge_base it.

Inferred read-only

CONNECT WITH APPROVAL

Client installation

Review this server and its permissions before adding it. Secret placeholders must be set locally.

Codex

~/.codex/config.toml

[mcp_servers.kit-for-ai]
url = "https://kitforai.com/api/mcp"
enabled = true

Claude Code

.mcp.json

{
  "mcpServers": {
    "kit-for-ai": {
      "type": "http",
      "url": "https://kitforai.com/api/mcp"
    }
  }
}

Claude Desktop

Settings → Connectors → Add custom connector

Name: kit-for-ai
Remote MCP URL: https://kitforai.com/api/mcp

Add this remote URL as a custom connector in Claude Desktop. Availability depends on the user plan and workspace policy.

Cursor

.cursor/mcp.json

{
  "mcpServers": {
    "kit-for-ai": {
      "url": "https://kitforai.com/api/mcp"
    }
  }
}

Visual Studio Code

.vscode/mcp.json

Add to Visual Studio Code

{
  "servers": {
    "kit-for-ai": {
      "type": "http",
      "url": "https://kitforai.com/api/mcp"
    }
  }
}

Generic MCP

Client-specific MCP configuration

{
  "name": "kit-for-ai",
  "transport": "streamable-http",
  "url": "https://kitforai.com/api/mcp"
}

MCP Inspector

Run the official MCP Inspector locally and enter the indexed Streamable HTTP endpoint.

TRUST AND VERIFICATION EVIDENCE

Trust Data Available

BuiltWith Trust API v2 evidence for kitforai.com was fetched 2026-09-01T20:02:18.047Z.

Trust status Neutral

kitforai.com is assessed as Neutral: No suspicious signals found, but no strong positive signal either

Indexed

Evidence is source-attributed and does not guarantee that a third-party server is safe. Risk labels are conservative metadata heuristics.