Docs
Agent setup for Scry
Connect Claude Code, Codex, or another agent to Scry over MCP, or give it an API key for the HTTP API, and let it compose bounded SQL over public corpus sources.
Connect over MCP
Scry is an MCP server at https://mcp.scry.io. Add that URL to your agent and approve the sign-in when it asks; the agent then has scry_context, scry_schema, scry_query, scry_embed, search, fetch, and scry_feedback as tools. Per-client steps for ChatGPT, Claude.ai, Claude Desktop, Claude Code, Codex, and Cursor are in Connect. Headless runs pass an API key as a bearer header instead of signing in.
claude mcp add --transport http scry https://mcp.scry.io codex mcp add scry --url https://mcp.scry.io && codex mcp login scry
HTTP API and the environment variable
Agents without an MCP client use the HTTP API at https://api.scry.io with SCRY_API_KEY as the bearer credential on every request. Keep the key in ~/.config/scry/env. Every query runs authenticated: under an account key, or per query via x402 payment authorization.
Get a key
The dashboard at https://scry.io/dashboard holds your personal key. From code: create an account with the first request (its response returns a session_token), then mint a key with the second. Queries run only after the email address is verified; wallet-signed agent accounts (POST /v1/auth/agent/signup) are verified by the signature and need no inbox. The scry product scope is required alongside capability scopes, and the key is shown once. Query access needs scry plus read or write; vector minting needs scry plus embed or write.
curl -X POST https://api.scry.io/v1/auth/signup \
-H "Content-Type: application/json" \
-d '{"email":"...","password":"..."}'
curl -X POST https://api.scry.io/v1/auth/api-keys \
-H "Authorization: Bearer <session_token>" \
-H "Content-Type: application/json" \
-d '{"name":"agent","scopes":["scry","read"]}' | Scope | Purpose |
|---|---|
| scry | Product scope; required alongside query and embedding capability scopes. |
| read | Read capability; with scry, permits queries. |
| write | Write capability; with scry, permits queries and vector minting. |
| billing | Billing capability. |
| embed | Vector-minting capability; with scry, permits POST /v1/scry/embed. |
| rerank | Reranking capability. |
| ingest | Ingestion capability. |
| rate | Rate-management capability. |
| account | Account-management capability. |
Agent context
Whichever door, the agent calls scry_context (GET /v1/scry/context?mode=agent) once per session and scry_schema (GET /v1/scry/schema) before writing SQL. The live context carries endpoints, access, and current guidance; the schema is the only discovery authority.
Optional local skill
Install the packaged skill when you want local query patterns and schema notes beside the agent.
npx --yes skills@latest add exopriors/skills