MCP Server
MCP
io.github.Coalesce-Software-Inc/coalesce-transform
By MCP server for managing Coalesce Transform workspaces, nodes, pipelines, and runs.
Install
npx -y [email protected]Configuration Example
{
"remotes": [],
"packages": [
{
"registryType": "npm",
"identifier": "coalesce-transform-mcp",
"version": "0.10.1",
"transport": {
"type": "stdio"
},
"environmentVariables": [
{
"description": "Bearer token from the Coalesce Deploy tab. Optional when `~/.coa/config` provides a `token`.",
"format": "string",
"isSecret": true,
"name": "COALESCE_ACCESS_TOKEN"
},
{
"description": "Selects which `~/.coa/config` profile to load. Defaults to default.",
"format": "string",
"name": "COALESCE_PROFILE"
},
{
"description": "Region-specific base URL. Defaults to https://app.coalescesoftware.io (US).",
"format": "string",
"name": "COALESCE_BASE_URL"
},
{
"description": "Fallback org ID for cancel-run. Also readable from `orgID` in the active ~/.coa/config profile.",
"format": "string",
"name": "COALESCE_ORG_ID"
},
{
"description": "Local repo root for repo-backed tools and pipeline planning. Also readable from `repoPath` in the active ~/.coa/config profile.",
"format": "string",
"name": "COALESCE_REPO_PATH"
},
{
"description": "Base directory for the local data cache. When set, cache files are written here instead of the working directory. Also readable from `cacheDir` in the active ~/.coa/config profile.",
"format": "string",
"name": "COALESCE_CACHE_DIR"
},
{
"description": "JSON size threshold before auto-caching to disk. Defaults to 32768.",
"format": "string",
"name": "COALESCE_MCP_AUTO_CACHE_MAX_BYTES"
},
{
"description": "Forces large responses inline as text instead of auto-caching them to disk and returning a `resource_link` (and suppresses per-field cache resource links). The server already auto-enables this for clients known not to support MCP resources (e.g. Snowflake Cortex), which otherwise render the link as unreadable \"binary data\" and retry in a loop. Set `true` to force it on for an unrecognised client, or `false` to disable auto-detection. Leave unset for Claude/Cursor to keep large payloads out of context. Defaults to false (auto-enabled for resource-less clients).",
"format": "string",
"name": "COALESCE_MCP_INLINE_RESPONSES"
},
{
"description": "In-memory lineage cache TTL in milliseconds. Defaults to 1800000.",
"format": "string",
"name": "COALESCE_MCP_LINEAGE_TTL_MS"
},
{
"description": "Max outbound API request body size. Defaults to 524288.",
"format": "string",
"name": "COALESCE_MCP_MAX_REQUEST_BODY_BYTES"
},
{
"description": "Default per-request timeout for Coalesce API calls. Raise on large workspaces where paginated reads exceed the default. Defaults to 60000.",
"format": "string",
"name": "COALESCE_MCP_REQUEST_TIMEOUT_MS"
},
{
"description": "Per-page timeout for detail=true paginated fetches of large node lists. Defaults to 180000.",
"format": "string",
"name": "COALESCE_MCP_DETAIL_FETCH_TIMEOUT_MS"
},
{
"description": "Deadline for the best-effort workspace-adoption node-type ranking lookup inside node creation. Advisory only — creation proceeds without a ranking suggestion if this trips. Defaults to 15000.",
"format": "string",
"name": "COALESCE_MCP_NODE_TYPE_RANKING_TIMEOUT_MS"
},
{
"description": "In-memory TTL for the workspace node-type inventory. Set to `0` to disable. Defaults to 300000.",
"format": "string",
"name": "COALESCE_MCP_INVENTORY_CACHE_TTL_MS"
},
{
"description": "In-memory TTL for the workspace node-index (id/name/type/location) cache used by SQL- and intent-ref resolution. Set to `0` to disable. Defaults to 300000.",
"format": "string",
"name": "COALESCE_MCP_NODE_INDEX_CACHE_TTL_MS"
},
{
"description": "In-memory TTL for the workspace node-detail (full body) cache used by review and predecessor lookups. Set to `0` to disable. Defaults to 300000.",
"format": "string",
"name": "COALESCE_MCP_NODE_DETAIL_CACHE_TTL_MS"
},
{
"description": "When `true`, hides all write/mutation tools during registration. Only read, list, search, cache, analyze, review, diagnose, and plan tools are exposed. Defaults to false.",
"format": "string",
"name": "COALESCE_MCP_READ_ONLY"
},
{
"description": "Directory for customizable AI skill resources. When set, reads context resources from this directory and seeds defaults on first run. Users can augment or override any skill.",
"format": "string",
"name": "COALESCE_MCP_SKILLS_DIR"
},
{
"description": "Snowflake account identifier (e.g., `abc12345.us-east-1`). Required by the local `coa` CLI and `coa doctor`; not used by the MCP's REST run path. (required for run tools)",
"format": "string",
"name": "SNOWFLAKE_ACCOUNT"
},
{
"description": "Snowflake account username (required for run tools)",
"format": "string",
"name": "SNOWFLAKE_USERNAME"
},
{
"description": "Path to PEM-encoded private key (required if SNOWFLAKE_PAT not set)",
"format": "string",
"name": "SNOWFLAKE_KEY_PAIR_KEY"
},
{
"description": "Snowflake Programmatic Access Token (alternative to key pair)",
"format": "string",
"isSecret": true,
"name": "SNOWFLAKE_PAT"
},
{
"description": "Passphrase for encrypted keys",
"format": "string",
"isSecret": true,
"name": "SNOWFLAKE_KEY_PAIR_PASS"
},
{
"description": "Snowflake compute warehouse (required for run tools)",
"format": "string",
"name": "SNOWFLAKE_WAREHOUSE"
},
{
"description": "Snowflake user role (required for run tools)",
"format": "string",
"name": "SNOWFLAKE_ROLE"
}
]
}
]
}
mcp
model-context-protocol
npm
Comments
Sign in to leave a comment