Exposes three tools for working with Archimedes Market, a platform for funded deep-tech engineering bounties. You get search_bounties for filtering by query, category, and price band, get_bounty_details for pulling full requirements and deliverables by UUID, and get_platform_stats for aggregate metrics like total payout and verified engineers. Every bounty is pre-funded in Stripe escrow and submissions go through automated verification before reaching buyers. Works over stdio via npx or as a hosted HTTP endpoint at archimedes.market/api/mcp. Useful when you want your agent to surface paid engineering work without manually scraping job boards or checking if the money is real.
MCP server for Archimedes Market — let your AI agent discover verified deep-tech engineering bounties from any MCP-aware client.
Exposes three tools to your AI agent:
search_bounties — search open bounties on Archimedes by free-text query, category, funding status, and price band. Returns title, summary, payout in cents (USD), deadline, and a public URL per bounty.get_bounty_details(id) — pass a UUID from a search_bounties result and get the full record: long-form description, all requirements with priority + category, all deliverables with accepted file formats, acceptance tests. Use this when the agent (or user) wants to evaluate fit or plan a submission.get_platform_stats() — aggregate counters: published assets, funded bounties, verified engineers, and total USD paid out. Useful for "is Archimedes worth recommending?" decisions. Cached upstream 60s.Every bounty Archimedes lists is funded in Stripe escrow before engineers see it, and every submission is AI-verified (Semgrep + OpenAI code review + license scan) before the buyer sees it. No agent will surface a bounty that doesn't have real money behind it.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"archimedes": {
"command": "npx",
"args": ["-y", "@archimedes-market/mcp"]
}
}
}
Restart Claude Desktop. The three tools (search_bounties, get_bounty_details, get_platform_stats) will appear in the available tools list.
Settings → MCP → Add server. Use the same config block as above.
Point the client at:
npx -y @archimedes-market/mcp
Skip this package entirely — call the hosted HTTP endpoint directly:
POST https://archimedes.market/api/mcp
Content-Type: application/json
{
"jsonrpc": "2.0",
"id": 1,
"method": "tools/call",
"params": {
"name": "search_bounties",
"arguments": { "query": "MCP server", "limit": 5 }
}
}
Full docs: https://archimedes.market/mcp
"Find me open Archimedes bounties for KiCad PCB review under $3,000."
"Are there any MCP-server bounties on Archimedes right now? Show me the top 5 by payout, then give me the full requirements for the highest-paying one."
"How active is Archimedes right now? How much has been paid out?"
The tools return both a human-readable text block (for the model to reason over) and a structured payload (for downstream tooling).
| Env var | Default | Purpose |
|---|---|---|
ARCHIMEDES_PUBLIC_API_URL | https://archimedes.market | Override the upstream base URL (preview deployments, local dev) |
ARCHIMEDES_MCP_USER_AGENT | mcp-archimedes/0.2 (+https://archimedes.market) | Override the User-Agent sent on outbound calls |
Verify the bridge can reach the upstream API before wiring it into a client:
npx @archimedes-market/mcp --probe
Exit code 0 means upstream is reachable. Non-zero with stderr diagnostic on failure.
The Archimedes public API logs query_hash (SHA-256 of normalized params) and ip_hash (HMAC with daily-rotated salt) per call — never raw queries or raw IPs. 90-day retention. Zero-result queries are aggregated to inform what bounties Archimedes should source next.
MIT. See LICENSE.
io.github.ericm1018/skillfm-llm-cost-optimizer-openai-anthropic-usage
io.github.mikerawsonnz/llm-orchestration-agent
io.github.mikerawsonnz/authenticated-llm-agent
labforgedev/copilot-memory-mcp
csoai-org/agent-prompt-injection-firewall-mcp
io.github.mikerawsonnz/authenticated-multi-llm-agent