Skip to main content
Configure once, works everywhere. Connectors added at claude.ai/customize/connectors automatically sync to Claude Code CLI when you’re signed into the same Anthropic account — no duplicate setup needed. The Claude Code .mcp.json project file is also shared with the VS Code extension and Claude Code on the web.

​
Claude.ai (web)

Go to claude.ai/customize/connectors, click Add connector, and enter:
  • URL: https://api.askalchemist.com/mcp/
  • Auth: Bearer token → alch_YOUR_KEY
Once saved, Alchemist tools are live in claude.ai chat and automatically available in Claude Code CLI on the same account.

​
Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows): 
{
  "mcpServers": {
    "alchemist": {
      "url": "https://api.askalchemist.com/mcp/",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}
Then import it into Claude Code in one command: 
claude mcp add-from-claude-desktop

​
Claude Code — copy-paste setup

Copy and Paste in Claude Code

Copy the block below and paste it into Claude Code. Claude will automatically register the MCP server and create the skill for you.
Step 1: Install or update Alchemist MCP

If Alchemist MCP already exists in your MCP config, uninstall it first or update the
endpoint below. Run this command in your terminal:

claude mcp add --transport http alchemist "https://api.askalchemist.com/mcp/" \
  --header "Authorization: Bearer YOUR_KEY"


Step 2: Add the Alchemist skill

Save this file to ~/.claude/skills/alchemist-research/SKILL.md

---
name: alchemist-research
description: Financial research using the Alchemist database. Searches thousands of pre-processed primary source documents — FOMC minutes, USDA WASDE reports, SEC filings, BLS/BEA data releases — and returns citable insights with verbatim source quotes. Use for any macro, earnings, regulatory, or commodity research question.
context: fork
---

# Alchemist Financial Research

## Primary Tool

Always use `search_insights` first for any financial research question.
Do NOT jump to `search_web` before trying `search_insights`.

## Query Format (Critical)

Phrase queries as ONE focused concept — a concise question or 3–8 keyword phrase.

Good:
- "Did the March 2026 FOMC minutes signal a rate pause?"
- "Fed dot plot rate path 2026"
- "AAPL Q3 2025 revenue guidance"
- "corn ending stocks USDA WASDE"

Bad:
- "Tell me about the Federal Reserve and interest rates and inflation" (conversational wrapper + keyword soup)
- "What does Wall Street think?" (too vague, no anchor entity)

## Workflow

1. Call `list_filter_options` if you need to filter by source name
2. Run 1–2 targeted searches, read results, then refine
3. If sparse results: retry with different phrasing or remove date/source filters
4. For deep research: get `doc_id` from search results, call `get_document` for full context
5. Fall back to `search_web` ONLY after `search_insights` returns nothing relevant

## Token Isolation

Never run large searches in the main context. Spawn a subagent:
- Subagent runs the search internally
- Subagent distills results into compact output
- Subagent returns findings to main context
- Main context stays clean regardless of result volume

## Citation Format

Always cite source_name and published_date for every insight surfaced:
> "Per the Federal Reserve FOMC Minutes (March 2026)..."

## Output Format

Return:
1. Key findings — one insight per line, attributed
2. Sources — document URL + publication date
3. Notes — any gaps, conflicts, or low-confidence areas


Step 3: Restart Claude Code

Ask the user to restart Claude Code so the new MCP connection takes effect.

​
Manual setup

​
Claude Desktop

Edit ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows): 
{
  "mcpServers": {
    "alchemist": {
      "url": "https://api.askalchemist.com/mcp/",
      "headers": {
        "Authorization": "Bearer YOUR_KEY"
      }
    }
  }
}
Restart Claude Desktop to apply.

​
Claude API (function calling)

If you’re calling the Claude API directly, define search_insights as a tool and handle the tool-use loop yourself: 
import anthropic, httpx

client = anthropic.Anthropic()

tools = [{
    "name": "search_insights",
    "description": "Search the Alchemist financial research database. Returns citable insights with verbatim source quotes. Query as a focused 3–8 word phrase or concise question.",
    "input_schema": {
        "type": "object",
        "properties": {
            "query": {"type": "string"},
            "source_name": {"type": "string"},
            "since": {"type": "string", "format": "date"},
            "limit": {"type": "integer", "default": 20}
        },
        "required": ["query"]
    }
}]

def call_alchemist(name, inputs):
    if name == "search_insights":
        return httpx.post(
            "https://api.askalchemist.com/api/insights/search",
            headers={"X-API-Key": "YOUR_KEY"},
            json=inputs,
        ).json()