// MCP TOOL REFERENCE

COALESCE TRANSFORM TOOLS

100 tools from the Coalesce Transform MCP Server, categorised by risk level.

// ALL 100 COALESCE TRANSFORM TOOLS

READ 25 tools

Read `clear_data_cache` Delete all cached snapshots, auto-cached responses, and plan summaries ⚠️ Read `get_environment_job` Get details of a specific job Read `get_environment_node` Get a specific environment node Read `get_environment_overview` Environment details with full node list Read `get_environment` Get details of a specific environment Read `get_git_account` Get git account details Read `get_pipeline_workshop_status` Get the current state of a workshop session Read `get_project` Get project details Read `get_user_roles` Get roles for a specific user Read `get_workspace_node` Get a specific workspace node Read `get_workspace` Get details of a specific workspace Read `list_environment_jobs` List all jobs for an environment Read `list_environment_nodes` List nodes in an environment Read `list_environments` List all available environments Read `list_git_accounts` List all git accounts Read `list_org_users` List all organization users Read `list_projects` List all projects Read `list_repo_node_types` List exact resolvable committed node-type identifiers from `nodeTypes/` Read `list_repo_packages` List package aliases and enabled node-type coverage from a committed Coalesce repo Read `list_runs` List runs with optional filters Read `list_user_roles` List all user roles Read `list_workspace_node_types` List distinct node types observed in current workspace nodes Read `list_workspace_nodes` List nodes in a workspace Read `list_workspaces` List all workspaces Read `search_workspace_content` Search node SQL, column names, descriptions, and config values

WRITE 52 tools

Write `analyze_impact` Downstream impact of changing a node or specific column - impacted counts, grouped by depth, and critical path Write `analyze_workspace_patterns` Detect package adoption, pipeline layers, methodology, and generate recommendations Write `apply_join_condition` Auto-generate and write a FROM/JOIN/ON clause for a multi-predecessor node Write `apply_sql_to_workspace_node` Round-trip user edits on rendered DDL/DML SQL (`coa_dry_run_create` / `coa_dry_run_run` output) back into a... Write `audit_documentation_coverage` Scan all workspace nodes/columns for missing descriptions Write `cache_environment_nodes` Fetch every page of environment nodes, write a full snapshot Write `cache_org_users` Fetch every page of organization users, write a full snapshot Write `cache_workspace_nodes` Fetch every page of workspace nodes, write a full snapshot, and return cache metadata Write `complete_node_configuration` Intelligently complete a node's configuration by analyzing context Write `convert_join_to_aggregation` Convert a join-style node into an aggregated fact-style node Write `create_environment` Create a new environment within a project Write `create_git_account` Create a new git account Write `create_node_from_external_schema` Create a workspace node whose columns match an existing warehouse table or external schema Write `create_pipeline_from_sql` Plan and create a pipeline directly from SQL Write `create_project` Create a new project Write `create_workspace_job` Create a job in a workspace with node include/exclude selectors Write `create_workspace_node_from_predecessor` Create a node from predecessor nodes with column coverage verification Write `create_workspace_node_from_scratch` Create a workspace node with no predecessors Write `create_workspace_subgraph` Create a subgraph to group nodes visually Write `diagnose_setup` Stateless probe reporting configured setup pieces; pairs with the `/coalesce-setup` MCP prompt Write `find_jobs_by_name` Fuzzy-match environment jobs by name and return each match with its recent runs Write `generate_set_workspace_node_template_from_variant` Generate a template from a committed corpus variant Write `generate_set_workspace_node_template` Generate a YAML-friendly `set_workspace_node` body template Write `get_column_lineage` Trace a column through the pipeline upstream and downstream Write `get_downstream_nodes` Walk the full downstream dependency graph for a node Write `get_node_type_variant` Load one exact node-type corpus variant by variant key Write `get_repo_node_type_definition` Resolve one node type and return its outer definition plus parsed `nodeMetadataSpec` Write `get_upstream_nodes` Walk the full upstream dependency graph for a node Write `get_workspace_subgraph` Get details of a specific subgraph by UUID (the public API has no subgraph list endpoint — look up UUIDs vi... Write `list_job_nodes` Resolve a workspace job's selectors into concrete nodes, grouped by subgraph Write `parse_disk_node_to_workspace_body` Convert an on-disk coa node YAML back into a cloud workspace-node body for `set_workspace_node` / `update_w... Write `parse_sql_structure` Parse a SQL statement into structural components (CTEs, source tables, projected columns) without touching ... Write `personalize_skills` Export bundled skill files to a local directory for customization Write `pipeline_workshop_close` Close a workshop session and release resources Write `pipeline_workshop_instruct` Send a natural language instruction to modify the current workshop plan Write `pipeline_workshop_open` Open an iterative pipeline builder session with workspace context pre-loaded Write `plan_pipeline` Plan a pipeline from SQL or a natural-language goal without mutating the workspace; ranks best-fit node typ... Write `propagate_column_change` Update all downstream columns after a column rename or data type change ⚠️ Write `replace_workspace_node_columns` Replace `metadata.columns` wholesale Write `review_pipeline` Analyze an existing pipeline for redundant nodes, missing joins, layer violations, naming issues, and optim... Write `run_status` Check status of a running job Write `search_node_type_variants` Search the committed node-type corpus by normalized family, package, primitive, or support status Write `select_pipeline_node_type` Rank and select the best Coalesce node type for a pipeline step Write `set_env_role` Set environment role for a user Write `set_org_role` Set organization role for a user Write `set_project_role` Set project role for a user Write `set_workspace_node` Replace a workspace node with a full body Write `update_git_account` Update a git account Write `update_project` Update a project Write `update_workspace_job` Update a job's name and node selectors Write `update_workspace_node` Safely update selected fields of a workspace node Write `update_workspace_subgraph` Update a subgraph's name and node membership

DESTRUCTIVE 10 tools

EXECUTE 13 tools

Execute `build_pipeline_from_intent` Build a pipeline from a natural language goal with automatic entity resolution and node type selection Execute `cache_runs` Fetch every page of run results, write a full snapshot Execute `create_pipeline_from_plan` Execute an approved pipeline plan using predecessor-based creation Execute `diagnose_run_failure` Classify errors, surface root cause, suggest actionable fixes Execute `get_environment_health` Dashboard: node counts, run statuses, failed runs in last 24h, stale nodes, dependency health Execute `get_job_run_details_by_name` Fuzzy-match one environment job by name and return its latest run details + results Execute `get_run_details` Run metadata plus results in one call Execute `get_run_results` Get results of a completed run Execute `get_run` Get details of a specific run Execute `retry_and_wait` Retry a failed run and poll until completion Execute `retry_run` Retry a failed run Execute `run_and_wait` Start a run and poll until completion Execute `start_run` Start a new run; requires Snowflake auth

// FAQ

How many tools does the Coalesce Transform MCP server have? +

The Coalesce Transform MCP server exposes 100 tools across 4 categories: Read, Write, Destructive, Execute.

How do I enforce policies on Coalesce Transform tools? +

Route the Coalesce Transform server through the PolicyLayer gateway. Define allow, deny, or approval rules per tool in the dashboard — they are enforced on every call before it reaches the server.

What risk categories do Coalesce Transform tools fall into? +

Coalesce Transform tools are categorised as Read (25), Write (52), Destructive (10), Execute (13). Each category has a recommended default policy.

Let agents act without letting them run wild.

Route your MCP servers through PolicyLayer and every tool call is checked against your policy before it runs — allow, deny, or require approval. Per-identity grants. Full audit log. Live in minutes.

SECURE YOUR MCP →

Free to start. No card required.

4,600+ MCP servers and 31,000+ tools scanned and risk-classified.