recce-mcp-e2e — dbt project validation recce-mcp-e2e, recce, DataRecce, community, dbt project validation, ai agent skill, mcp server, agent automation, data validation toolkit, MCP tool verification, full stack verification, data engineering workflow

v1.0.0
GitHub

About this Skill

Perfect for Data Engineering Agents needing comprehensive dbt project validation and MCP tool verification. recce-mcp-e2e is a full-stack verification toolkit for dbt projects, ensuring data validation and integrity.

Features

Invokes full-stack verification via `/recce-mcp-e2e` command
Supports project directory specification using `/recce-mcp-e2e <project_path>`
Validates all 8 MCP tools against a real dbt project
Verifies single-env logic and error classification
Runs before merging MCP-related PRs

# Core Topics

dbt project validation data validation toolkit MCP tool verification full stack verification data engineering workflow dbt PR review
DataRecce DataRecce
[447]
[25]
Updated: 3/19/2026

↓ Quality Score

Top 5%
70
Excellent
Based on code quality & docs
Installation
SYS Universal Install (Auto-Detect)
> npx killer-skills add DataRecce/recce/recce-mcp-e2e
Supports 18+ Platforms
Cursor
Windsurf
VS Code
Trae
Claude
OpenClaw
+12 more

Agent Capability Analysis

The recce-mcp-e2e MCP Server by DataRecce is an open-source community integration for Claude and other AI agents, enabling seamless task automation and capability expansion. Optimized for dbt project validation, data validation toolkit, MCP tool verification.

Ideal Agent Persona

Perfect for Data Engineering Agents needing comprehensive dbt project validation and MCP tool verification.

Core Value

Empowers agents to perform full-stack verification of MCP tools against real dbt projects, utilizing Python and providing enhanced data-validation capabilities for dbt PR review, including error classification and single-env logic checks.

↓ Capabilities Granted for recce-mcp-e2e MCP Server

Verifying MCP tool functionality against dbt projects
Validating dbt project configurations and data pipelines
Debugging MCP-related issues in dbt projects

! Prerequisites & Limits

  • Requires modification of `recce/mcp_server.py` or `_tool_*` handlers
  • Limited to dbt projects and MCP tools
  • Not suitable for unit test changes only, frontend-only changes, or docs-only changes
Project
SKILL.md
2.8 KB
.cursorrules
1.2 KB
package.json
240 B
Ready
UTF-8
SKILL.md
Readonly

MCP E2E Verification

Full-stack verification of all 8 MCP tools against a real dbt project.

When to Use

  • After modifying recce/mcp_server.py or _tool_* handlers
  • After changing single-env logic or error classification
  • Before merging any MCP-related PR
  • Not for: unit test changes only, frontend-only changes, docs-only changes

Usage

Invoke as /recce-mcp-e2e or /recce-mcp-e2e <project_path>.

  • With argument: use the given path as the dbt project directory
  • Without argument: ask the user for the dbt project path

The project directory must contain target/manifest.json and target-base/manifest.json.

Process

  1. Resolve project path from argument or user input
  2. Validate target/ and target-base/ exist with manifest.json
  3. Detect recce source — find the repo root containing recce/mcp_server.py. If recce-nightly is also installed (pip show recce recce-nightly), set PYTHONPATH=<RECCE_REPO_ROOT>:$PYTHONPATH
  4. Generate test_mcp_e2e.py in the project directory from test_mcp_e2e_template.py (in this skill directory). Replace PROJECT_DIR_PLACEHOLDER with the resolved absolute path.
  5. Execute with appropriate PYTHONPATH prefix
  6. Report results — all 13 checks must show PASS. Expected output: 
    === FULL MODE (8 tools) ===
  PASS lineage_diff: PASS
  ...
=== SINGLE-ENV MODE ===
  PASS row_count_diff (_warning): PASS
  ...
ALL PASS
  7. Clean up — delete test_mcp_e2e.py

Quick Reference

Test SuiteChecksWhat's Verified
Full mode (8 tools)lineage_diff, schema_diff, row_count_diff, query, query_diff, profile_diff, list_checks, run_checkNon-empty results from each tool
Single-env _warning (3)row_count_diff, query_diff, profile_diff_warning field present with SINGLE_ENV_WARNING
Single-env no _warning (2)lineage_diff, schema_diff_warning field NOT present

Additional manual checks (not in script):

CheckCommand/Action
--helprecce mcp-server --help shows Prerequisites section
Server modesNon-server mode: list_tools returns only lineage_diff + schema_diff

Common Mistakes

ProblemFix
ImportError: cannot import name 'SINGLE_ENV_WARNING'recce-nightly conflict — use PYTHONPATH=<RECCE_REPO_ROOT>:$PYTHONPATH
lineage_diff returns emptyUse view_mode="all" (default changed_models filters out unchanged)
list_checks returns emptyPreset checks from recce.yml must be loaded via load_preset_checks() — script handles this
portalocker FileNotFoundError on exitCosmetic thread error in event collector — does not affect results
Single-env test uses target-baseBy design — load_context needs both, single_env=True flag simulates the mode

FAQ & Installation Steps

These questions and steps mirror the structured data on this page for better search understanding.

? Frequently Asked Questions

What is recce-mcp-e2e?

Perfect for Data Engineering Agents needing comprehensive dbt project validation and MCP tool verification. recce-mcp-e2e is a full-stack verification toolkit for dbt projects, ensuring data validation and integrity.

How do I install recce-mcp-e2e?

Run the command: npx killer-skills add DataRecce/recce/recce-mcp-e2e. It works with Cursor, Windsurf, VS Code, Claude Code, and 15+ other IDEs.

What are the use cases for recce-mcp-e2e?

Key use cases include: Verifying MCP tool functionality against dbt projects, Validating dbt project configurations and data pipelines, Debugging MCP-related issues in dbt projects.

Which IDEs are compatible with recce-mcp-e2e?

This skill is compatible with Cursor, Windsurf, VS Code, Trae, Claude Code, OpenClaw, Aider, Codex, OpenCode, Goose, Cline, Roo Code, Kiro, Augment Code, Continue, GitHub Copilot, Sourcegraph Cody, and Amazon Q Developer. Use the Killer-Skills CLI for universal one-command installation.

Are there any limitations for recce-mcp-e2e?

Requires modification of `recce/mcp_server.py` or `_tool_*` handlers. Limited to dbt projects and MCP tools. Not suitable for unit test changes only, frontend-only changes, or docs-only changes.

↓ How To Install

  1. 1. Open your terminal

    Open the terminal or command line in your project directory.

  2. 2. Run the install command

    Run: npx killer-skills add DataRecce/recce/recce-mcp-e2e. The CLI will automatically detect your IDE or AI agent and configure the skill.

  3. 3. Start using the skill

    The skill is now active. Your AI agent can use recce-mcp-e2e immediately in the current project.

Related Skills

Looking for an alternative to recce-mcp-e2e or building a community AI Agent? Explore these related open-source MCP Servers.

View All

widget-generator

Logo of f
f

widget-generator is an open-source AI agent skill for creating widget plugins that are injected into prompt feeds on prompts.chat. It supports two rendering modes: standard prompt widgets using default PromptCard styling and custom render widgets built as full React components.

★ 149.6k
⑂ 0
Design

linear

Logo of lobehub
lobehub

Linear is a workflow management system that enables multi-agent collaboration, effortless agent team design, and introduces agents as the unit of work interaction.

★ 73.4k
⑂ 0
Communication

testing

Logo of lobehub
lobehub

Testing is a process for verifying AI agent functionality using commands like bunx vitest run and optimizing workflows with targeted test runs.

★ 73.3k
⑂ 0
Communication

chat-sdk

Logo of lobehub
lobehub

chat-sdk is a unified TypeScript SDK for building chat bots across multiple platforms, providing a single interface for deploying bot logic.

★ 73.0k
⑂ 0
Communication