Skip to content

Search these docs from your AI tool

  • Antigravity
    {
      "mcpServers": {
        "edisyl-docs": {
          "serverUrl": "https://docs.edisyl.com/mcp"
        }
      }
    }
  • Claude CodeCLI
    claude mcp add edisyl-docs https://docs.edisyl.com/mcp --transport http --scope user
  • CodexCLI
    codex mcp add --url https://docs.edisyl.com/mcp edisyl-docs
  • Cursor
    {
      "mcpServers": {
        "edisyl-docs": {
          "type": "http",
          "url": "https://docs.edisyl.com/mcp"
        }
      }
    }
  • Gemini CLI
    gemini mcp add --transport http edisyl-docs https://docs.edisyl.com/mcp
  • Goose
    {
      "extensions": {
        "edisyl-docs": {
          "enabled": true,
          "name": "edisyl-docs",
          "type": "streamable_http",
          "uri": "https://docs.edisyl.com/mcp",
          "envs": {},
          "env_keys": [],
          "headers": {},
          "description": "",
          "timeout": 300,
          "bundled": null,
          "available_tools": []
        }
      }
    }
  • JetBrains AI Assistant
    {
      "mcpServers": {
        "edisyl-docs": {
          "type": "http",
          "url": "https://docs.edisyl.com/mcp"
        }
      }
    }

    Paste into Settings → Tools → AI Assistant → Model Context Protocol → Add → As JSON. Direct file writing isn’t supported — JetBrains stores this per-version as XML.

  • Junie (JetBrains)
    {
      "mcpServers": {
        "edisyl-docs": {
          "url": "https://docs.edisyl.com/mcp"
        }
      }
    }
  • OpenCode
    {
      "mcp": {
        "edisyl-docs": {
          "type": "remote",
          "url": "https://docs.edisyl.com/mcp"
        }
      }
    }
  • VS CodeCLI
    code --add-mcp '{"name":"edisyl-docs","type":"http","url":"https://docs.edisyl.com/mcp"}'
  • Windsurf
    {
      "mcpServers": {
        "edisyl-docs": {
          "serverUrl": "https://docs.edisyl.com/mcp"
        }
      }
    }

    Supports both stdio and native HTTP connections.

Reusable connections

A connection holds credentials for a provider on the org — separate from any one data source, and org-scoped: edisyl connections list shows every connection the organization has, not just the ones a particular pack can query.

Reach for a connection instead of data-sources create when:

  • One account, several databases. A Snowflake account with a dozen databases only needs its credentials stored once; each database becomes its own data source (and its own pack) mounted on top.
  • The provider isn’t SQL. API providers like linear have no database to mount at all — they only ever exist as a connection, attached straight to a pack.
  1. Test the credentials. Same connector-specific config JSON as data-sources test-connection, just a different command:

    Terminal window
    edisyl connections test --provider postgres --config-file db.json
  2. Create the connection.

    Terminal window
    edisyl connections create --name "Snowflake prod" --provider snowflake --config-file sf.json

    For an API provider (Linear today), pipe the token instead of passing a config file, and attach it to a pack right away with --pack-id:

    Terminal window
    printf '%s' "$LINEAR_API_KEY" | edisyl connections create \
    --provider linear --name "Linear" --pack-id <pack-id> --token-stdin
  3. See what a SQL connection can reach.

    Terminal window
    edisyl connections databases <connection-id>
  4. Mount a database as a data source. --type/--config are skipped entirely — --connection-id reuses the stored credentials, and this path mounts directly onto the connection without creating a new one:

    Terminal window
    edisyl data-sources create --name "Analytics" --connection-id <connection-id> --database ANALYTICS

Attaching an existing connection to another pack

Section titled “Attaching an existing connection to another pack”

edisyl connections attach <connection-id> --pack-id <pack-id> is the API-provider equivalent of mounting a data source — it’s how the same Linear connection ends up available to a second pack without creating it twice.

Every data-sources and connections subcommand defaults to the authenticated profile’s org. --org-id <uuid> overrides it where an override actually makes sense — it isn’t registered on data-sources list (org-scoped by the auth token already) or on test-connection/connections test (validating an unsaved config, tied to no org yet).

Last updated on

Report incorrect code

Please provide a detailed description of the incorrect code.