# Contextual AI

> Use this tool when you need to enable AI assistants with advanced enterprise search and document navigation capabilities to access internal knowledge bases, comprehend large reports, and enhance information discovery across multiple domains. It solves problems of information retrieval and document understanding through single-agent and multi-agent implementations, and advanced document navigation with hierarchical structure analysis. It takes in documents and knowledge bases as inputs and outputs interpretable attributions and intelligent navigation results, making it ideal for enterprises and teams requiring conversational access to complex information.

Canonical page: https://skillsregistry.net/skills/contextualai-enterprise-search  
JSON: https://api.skillsregistry.net/v1/skills/contextualai-enterprise-search

## Description

This MCP server provides AI assistants with enterprise search and document navigation capabilities through Contextual AI's platform, featuring three distinct implementations: single-agent RAG for specific knowledge bases, multi-agent routing with automatic reranking to select the best agent from available options, and an advanced document navigator that leverages Contextual AI's parse API to enable intelligent navigation of complex documents through hierarchical structure analysis and page-based content retrieval. The document navigator implementation stands out by providing agentic RAG tools that go beyond naive retrieval, offering interpretable attributions via tool call traces as agents navigate documents using inferred metadata like table of contents and document hierarchy. Built with FastMCP framework and featuring token counting for context management, tiktoken integration, and support for both local files and URLs, it serves enterprises needing conversational access to internal knowledge bases, teams requiring intelligent document comprehension for large reports and manuals, and organizations where natural language interfaces enhance information discovery across multiple specialized knowledge domains.

## Trust

- **Trust score (0–1):** 0.50
- **Verification tier:** unverified

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** social-media
- **Updated:** 2026-05-25

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/contextualai-enterprise-search)
- **Repository:** <https://github.com/contextualai/contextual-mcp-server>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "contextualai-enterprise-search"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/contextualai-enterprise-search` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/contextualai-enterprise-search/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt