PluginBench
MCP Server
Active
MIT

io.github.Coalesce-Software-Inc/coalesce-transform MCP Server

io.github.Coalesce-Software-Inc/coalesce-transform

RepositoryRegistry

What is the io.github.Coalesce-Software-Inc/coalesce-transform MCP server?

MCP server for managing Coalesce Transform workspaces, nodes, pipelines, and runs.

How to install io.github.Coalesce-Software-Inc/coalesce-transform

Copy-paste configuration for popular MCP clients.

transport: stdio
Config generated by PluginBench — verify against the source before use.
Environment / auth
  • COALESCE_ACCESS_TOKEN
    secret

    Bearer token from the Coalesce Deploy tab. Optional when `~/.coa/config` provides a `token`.

  • COALESCE_PROFILE

    Selects which `~/.coa/config` profile to load. Defaults to default.

  • COALESCE_BASE_URL

    Region-specific base URL. Defaults to https://app.coalescesoftware.io (US).

  • COALESCE_ORG_ID

    Fallback org ID for cancel-run. Also readable from `orgID` in the active ~/.coa/config profile.

  • COALESCE_REPO_PATH

    Local repo root for repo-backed tools and pipeline planning. Also readable from `repoPath` in the active ~/.coa/config profile.

  • COALESCE_CACHE_DIR

    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.

  • COALESCE_MCP_AUTO_CACHE_MAX_BYTES

    JSON size threshold before auto-caching to disk. Defaults to 32768.

  • COALESCE_MCP_INLINE_RESPONSES

    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).

  • COALESCE_MCP_LINEAGE_TTL_MS

    In-memory lineage cache TTL in milliseconds. Defaults to 1800000.

  • COALESCE_MCP_MAX_REQUEST_BODY_BYTES

    Max outbound API request body size. Defaults to 524288.

  • COALESCE_MCP_REQUEST_TIMEOUT_MS

    Default per-request timeout for Coalesce API calls. Raise on large workspaces where paginated reads exceed the default. Defaults to 60000.

  • COALESCE_MCP_DETAIL_FETCH_TIMEOUT_MS

    Per-page timeout for detail=true paginated fetches of large node lists. Defaults to 180000.

  • COALESCE_MCP_NODE_TYPE_RANKING_TIMEOUT_MS

    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.

  • COALESCE_MCP_INVENTORY_CACHE_TTL_MS

    In-memory TTL for the workspace node-type inventory. Set to `0` to disable. Defaults to 300000.

  • COALESCE_MCP_NODE_INDEX_CACHE_TTL_MS

    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.

  • COALESCE_MCP_NODE_DETAIL_CACHE_TTL_MS

    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.

  • COALESCE_MCP_READ_ONLY

    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.

  • COALESCE_MCP_SKILLS_DIR

    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.

  • SNOWFLAKE_ACCOUNT

    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)

  • SNOWFLAKE_USERNAME

    Snowflake account username (required for run tools)

  • SNOWFLAKE_KEY_PAIR_KEY

    Path to PEM-encoded private key (required if SNOWFLAKE_PAT not set)

  • SNOWFLAKE_PAT
    secret

    Snowflake Programmatic Access Token (alternative to key pair)

  • SNOWFLAKE_KEY_PAIR_PASS
    secret

    Passphrase for encrypted keys

  • SNOWFLAKE_WAREHOUSE

    Snowflake compute warehouse (required for run tools)

  • SNOWFLAKE_ROLE

    Snowflake user role (required for run tools)

~/Library/Application Support/Claude/claude_desktop_config.json
{
  "mcpServers": {
    "coalesce-transform": {
      "command": "npx",
      "args": [
        "-y",
        "coalesce-transform-mcp"
      ],
      "env": {
        "COALESCE_ACCESS_TOKEN": "<YOUR_COALESCE_ACCESS_TOKEN>",
        "COALESCE_PROFILE": "<YOUR_COALESCE_PROFILE>",
        "COALESCE_BASE_URL": "<YOUR_COALESCE_BASE_URL>",
        "COALESCE_ORG_ID": "<YOUR_COALESCE_ORG_ID>",
        "COALESCE_REPO_PATH": "<YOUR_COALESCE_REPO_PATH>",
        "COALESCE_CACHE_DIR": "<YOUR_COALESCE_CACHE_DIR>",
        "COALESCE_MCP_AUTO_CACHE_MAX_BYTES": "<YOUR_COALESCE_MCP_AUTO_CACHE_MAX_BYTES>",
        "COALESCE_MCP_INLINE_RESPONSES": "<YOUR_COALESCE_MCP_INLINE_RESPONSES>",
        "COALESCE_MCP_LINEAGE_TTL_MS": "<YOUR_COALESCE_MCP_LINEAGE_TTL_MS>",
        "COALESCE_MCP_MAX_REQUEST_BODY_BYTES": "<YOUR_COALESCE_MCP_MAX_REQUEST_BODY_BYTES>",
        "COALESCE_MCP_REQUEST_TIMEOUT_MS": "<YOUR_COALESCE_MCP_REQUEST_TIMEOUT_MS>",
        "COALESCE_MCP_DETAIL_FETCH_TIMEOUT_MS": "<YOUR_COALESCE_MCP_DETAIL_FETCH_TIMEOUT_MS>",
        "COALESCE_MCP_NODE_TYPE_RANKING_TIMEOUT_MS": "<YOUR_COALESCE_MCP_NODE_TYPE_RANKING_TIMEOUT_MS>",
        "COALESCE_MCP_INVENTORY_CACHE_TTL_MS": "<YOUR_COALESCE_MCP_INVENTORY_CACHE_TTL_MS>",
        "COALESCE_MCP_NODE_INDEX_CACHE_TTL_MS": "<YOUR_COALESCE_MCP_NODE_INDEX_CACHE_TTL_MS>",
        "COALESCE_MCP_NODE_DETAIL_CACHE_TTL_MS": "<YOUR_COALESCE_MCP_NODE_DETAIL_CACHE_TTL_MS>",
        "COALESCE_MCP_READ_ONLY": "<YOUR_COALESCE_MCP_READ_ONLY>",
        "COALESCE_MCP_SKILLS_DIR": "<YOUR_COALESCE_MCP_SKILLS_DIR>",
        "SNOWFLAKE_ACCOUNT": "<YOUR_SNOWFLAKE_ACCOUNT>",
        "SNOWFLAKE_USERNAME": "<YOUR_SNOWFLAKE_USERNAME>",
        "SNOWFLAKE_KEY_PAIR_KEY": "<YOUR_SNOWFLAKE_KEY_PAIR_KEY>",
        "SNOWFLAKE_PAT": "<YOUR_SNOWFLAKE_PAT>",
        "SNOWFLAKE_KEY_PAIR_PASS": "<YOUR_SNOWFLAKE_KEY_PAIR_PASS>",
        "SNOWFLAKE_WAREHOUSE": "<YOUR_SNOWFLAKE_WAREHOUSE>",
        "SNOWFLAKE_ROLE": "<YOUR_SNOWFLAKE_ROLE>"
      }
    }
  }
}

Related MCP servers

SASAP ABAP MCP logo

SAP ABAP MCP

Active

Develop, test, analyze, and operate SAP ABAP systems through ADT from AI coding agents.

3
TypeScript
MIT
View repository →
IOio.github.Cocabadger/tick-mcp logo

io.github.Cocabadger/tick-mcp

Maintained

A time server that keeps your AI honest about time. Real clock + drift guard, zero dependencies.

6
Python
MIT
View repository →
IOio.github.CodeAlive-AI/codealive-mcp logo

io.github.CodeAlive-AI/codealive-mcp

Active

Semantic code search and analysis engine for AI assistants to understand large codebases with graph-based retrieval.

82
Python
MIT
View repository →
IO

io.github.CodeCraftersLLC/local-voice-mcp

Give your MCP clients the ability to speak by running local voice models using Chatterbox TTS

IOio.github.CodeLogicIncEngineering/codelogic-mcp-server logo

io.github.CodeLogicIncEngineering/codelogic-mcp-server

Active

Analyze code and database impact with Lineai's dependency graph in your AI assistant.

36
Python
MPL-2.0
View repository →
DDDDMarketer logo

DDMarketer

Active

Find and validate SaaS ideas from real user complaints, scored for commercial intent.

0
MIT
View repository →