streamwright-mcp 0.0.1__py3-none-any.whl

streamwright_mcp/__init__.py

@@ -0,0 +1,5 @@
+"""
+StreamWright Model Context Protocol (MCP) Server.
+"""
+
+__version__ = "0.1.0"

streamwright_mcp/cli.py

@@ -0,0 +1,26 @@
+"""
+CLI entry point for StreamWright MCP server.
+"""
+
+import argparse
+import sys
+from streamwright_mcp.server import server
+
+
+def main(argv=None) -> None:
+    parser = argparse.ArgumentParser(
+        description="StreamWright Model Context Protocol (MCP) server."
+    )
+    parser.add_argument(
+        "--transport",
+        choices=["stdio", "sse", "streamable-http"],
+        default="stdio",
+        help="MCP transport protocol (default: stdio)",
+    )
+    args = parser.parse_args(argv)
+
+    server.run(transport=args.transport)
+
+
+if __name__ == "__main__":
+    main()

streamwright_mcp/contracts.py

@@ -0,0 +1,217 @@
+"""
+Dynamic reflection and in-code contract inspection for StreamWright connectors.
+
+Zero duplication: extracts contracts, schemas, auth specifications, and execution
+behaviors directly from live Python connector modules and core schema definitions.
+"""
+
+import importlib
+import importlib.metadata
+import inspect
+from typing import Any, Dict, List, Optional
+
+from streamwright.core.validation import schema as core_schema
+from streamwright_mcp.hub import fetch_hub_connector, list_hub_connectors
+
+
+def list_installed_connectors() -> List[Dict[str, Any]]:
+    """
+    Discovers all StreamWright connectors installed in the current Python environment
+    using the 'streamwright.connectors' entry points group.
+    """
+    eps = importlib.metadata.entry_points()
+    if hasattr(eps, "select"):
+        group = eps.select(group="streamwright.connectors")
+    else:
+        group = eps.get("streamwright.connectors", [])
+
+    results = []
+    seen = set()
+
+    for ep in group:
+        if ep.name in seen:
+            continue
+        seen.add(ep.name)
+
+        try:
+            cls = ep.load()
+            spec = getattr(cls, "spec", None)
+            dist = getattr(ep, "dist", None)
+            version = dist.version if dist else None
+
+            results.append({
+                "name": ep.name,
+                "title": getattr(spec, "title", ep.name.replace("_", " ").title()) if spec else ep.name,
+                "category": getattr(spec, "category", "general") if spec else "general",
+                "transport": getattr(spec, "transport", "unknown") if spec else "unknown",
+                "version": version,
+                "installed": True,
+            })
+        except Exception as exc:
+            results.append({
+                "name": ep.name,
+                "title": ep.name,
+                "category": "error",
+                "transport": "unknown",
+                "version": None,
+                "installed": False,
+                "error": str(exc),
+            })
+
+    results.sort(key=lambda x: x["name"])
+    return results
+
+
+def get_connector_contract(name: str) -> Dict[str, Any]:
+    """
+    Retrieves the complete in-code contract for a connector.
+
+    If the connector is installed, extracts its 5-part contract from module/class docstrings,
+    its ConnectorSpec, auth schemas, and supported methods.
+    If not installed, returns Hub installation instructions.
+    """
+    eps = importlib.metadata.entry_points()
+    if hasattr(eps, "select"):
+        group = eps.select(group="streamwright.connectors")
+    else:
+        group = eps.get("streamwright.connectors", [])
+
+    matching_ep = None
+    for ep in group:
+        if ep.name == name:
+            matching_ep = ep
+            break
+
+    if matching_ep is not None:
+        try:
+            cls = matching_ep.load()
+            spec = getattr(cls, "spec", None)
+            mod = importlib.import_module(cls.__module__)
+            module_doc = inspect.getdoc(mod) or ""
+            class_doc = inspect.getdoc(cls) or ""
+
+            spec_info = {}
+            if spec:
+                spec_info = {
+                    "name": getattr(spec, "name", name),
+                    "title": getattr(spec, "title", name),
+                    "category": getattr(spec, "category", None),
+                    "transport": getattr(spec, "transport", None),
+                    "extension": getattr(spec, "extension", None),
+                    "package": getattr(spec, "package", None),
+                }
+
+            auth_required = getattr(cls, "auth_required", ())
+            auth_optional = getattr(cls, "auth_optional", ())
+            services = getattr(mod, "SERVICES", None) or getattr(cls, "SERVICES", None)
+            default_service = getattr(mod, "DEFAULT_SERVICE", None) or getattr(cls, "DEFAULT_SERVICE", None)
+
+            # Build full contract documentation
+            contract_doc = module_doc if module_doc else class_doc
+
+            return {
+                "name": name,
+                "installed": True,
+                "spec": spec_info,
+                "auth": {
+                    "required_fields": list(auth_required) if isinstance(auth_required, (list, tuple)) else auth_required,
+                    "optional_fields": list(auth_optional) if isinstance(auth_optional, (list, tuple)) else auth_optional,
+                },
+                "services": services,
+                "default_service": default_service,
+                "contract_documentation": contract_doc,
+            }
+        except Exception as exc:
+            return {
+                "name": name,
+                "installed": False,
+                "error": f"Failed to load installed connector: {exc}",
+            }
+
+    # Not installed: look up in StreamWright Hub
+    hub_data = fetch_hub_connector(name)
+    install_cmd = f"pip install streamwright-{name.replace('_', '-')}"
+    if hub_data and "install" in hub_data and isinstance(hub_data["install"], dict):
+        git_target = hub_data["install"].get("git")
+        if git_target:
+            install_cmd = f"pip install \"{git_target}\""
+
+    return {
+        "name": name,
+        "installed": False,
+        "message": f"Connector '{name}' is not installed in the current Python environment.",
+        "install_command": install_cmd,
+        "hub_metadata": hub_data or {
+            "title": name.replace("_", " ").title(),
+            "install_hint": install_cmd,
+        },
+    }
+
+
+def get_core_schema(kind: str = "all") -> Dict[str, Any]:
+    """
+    Returns the formal JSON schema and DSL documentation for StreamWright sources and streams.
+
+    Args:
+        kind: 'source', 'stream', or 'all' (default).
+    """
+    result: Dict[str, Any] = {
+        "version": core_schema.VERSION,
+        "supported_versions": list(core_schema.SUPPORTED_VERSIONS),
+        "kind": kind,
+    }
+
+    if kind in ("source", "all"):
+        result["source_schema"] = core_schema.json_schema()
+    if kind in ("stream", "all"):
+        result["stream_schema"] = core_schema.stream_json_schema()
+    if kind == "all":
+        result["dsl_specification"] = inspect.getdoc(core_schema) or ""
+
+    return result
+
+
+def get_cli_reference(command: Optional[str] = None) -> Dict[str, Any]:
+    """
+    Guides the AI assistant on how to inspect, discover, and execute StreamWright CLI commands.
+    Directs the LLM to run or inspect the live CLI help directly in the user's terminal/workspace.
+
+    Args:
+        command: Optional subcommand to inspect ('run', 'validate', 'connectors', 'mcp').
+    """
+    subcommand = (command or "").strip().lower()
+
+    if subcommand in ("run", "validate", "connectors", "mcp"):
+        return {
+            "binary": "streamwright",
+            "alias": "sw",
+            "command": subcommand,
+            "instruction": f"To get the most accurate and up-to-date options for '{subcommand}', inspect the CLI directly by running or checking: `sw {subcommand} --help` (or `streamwright {subcommand} --help`).",
+            "recommended_command": f"sw {subcommand} --help",
+            "fallback_command": f"python -m streamwright.core.cli {subcommand} --help",
+            "summary": {
+                "run": "Executes a pipeline source and exports records to Singer, JSONL, Parquet, DuckDB, or dlt.",
+                "validate": "Statically validates source and stream YAML configurations, refs, and DuckDB SQL.",
+                "connectors": "Lists installed connectors or searches/installs connectors from the StreamWright Hub.",
+                "mcp": "Runs the StreamWright Model Context Protocol server for AI coding assistants.",
+            }.get(subcommand, ""),
+        }
+
+    return {
+        "binary": "streamwright",
+        "alias": "sw",
+        "invocation_notes": "Both 'sw' and 'streamwright' are completely interchangeable.",
+        "instruction": "To discover all commands and live options, ask the user's terminal to inspect: `sw --help` (or `streamwright --help`). For specific subcommands, run `sw <command> --help`.",
+        "recommended_command": "sw --help",
+        "fallback_command": "python -m streamwright.core.cli --help",
+        "available_subcommands": {
+            "run": "sw run --help",
+            "validate": "sw validate --help",
+            "connectors": "sw connectors --help",
+            "mcp": "sw mcp --help",
+        },
+    }
+
+
+
+

streamwright_mcp/hub.py

@@ -0,0 +1,90 @@
+"""
+StreamWright Hub client for connector discovery.
+
+Used strictly as a fallback to discover connectors that are not installed locally.
+Does not cache to disk (no ~/.streamwright/connectors.json) and does not store auth or schema details.
+"""
+
+import logging
+from typing import Any, Dict, List, Optional
+import requests
+import yaml
+
+LOG = logging.getLogger("streamwright_mcp.hub")
+
+HUB_RAW_BASE = "https://raw.githubusercontent.com/karthick-jaganathan/streamwright-hub/main/connectors"
+HUB_INDEX_URL = "https://api.github.com/repos/karthick-jaganathan/streamwright-hub/contents/connectors"
+
+# Known official connectors for offline discovery fallback
+KNOWN_HUB_CONNECTORS = [
+    "restapi", "files", "s3", "gcs", "azure_blob", "postgres",
+    "mysql", "mongodb", "deltalake", "google_ads", "microsoft_ads",
+    "meta_ads", "openai_ads", "linkedin_ads", "amazon_ads", "apple_ads",
+]
+
+_MEM_CACHE: Dict[str, Dict[str, Any]] = {}
+
+
+def fetch_hub_connector(name: str, timeout: float = 3.0) -> Optional[Dict[str, Any]]:
+    """
+    Fetches connector metadata from the StreamWright Hub repository.
+    Returns None if unreachable or not found.
+    """
+    if name in _MEM_CACHE:
+        return _MEM_CACHE[name]
+
+    url = f"{HUB_RAW_BASE}/{name}.yaml"
+    try:
+        resp = requests.get(url, timeout=timeout)
+        if resp.status_code == 200:
+            data = yaml.safe_load(resp.text)
+            if isinstance(data, dict):
+                _MEM_CACHE[name] = data
+                return data
+    except Exception as exc:
+        LOG.debug("Failed to fetch connector %s from hub: %s", name, exc)
+
+    return None
+
+
+def list_hub_connectors(timeout: float = 3.0) -> List[Dict[str, Any]]:
+    """
+    Lists available connectors from the StreamWright Hub registry.
+    """
+    connectors = []
+    # Try fetching directory listing from GitHub API
+    try:
+        resp = requests.get(HUB_INDEX_URL, timeout=timeout)
+        if resp.status_code == 200:
+            items = resp.json()
+            for item in items:
+                name = item.get("name", "")
+                if name.endswith(".yaml"):
+                    conn_name = name[:-5]
+                    conn_data = fetch_hub_connector(conn_name, timeout=timeout)
+                    if conn_data:
+                        connectors.append(conn_data)
+                    else:
+                        connectors.append({
+                            "key": conn_name,
+                            "title": conn_name.replace("_", " ").title(),
+                            "install_hint": f"pip install streamwright-{conn_name.replace('_', '-')}"
+                        })
+            if connectors:
+                return connectors
+    except Exception as exc:
+        LOG.debug("Failed to list connectors from GitHub API: %s", exc)
+
+    # Fallback to known list
+    for name in KNOWN_HUB_CONNECTORS:
+        conn_data = fetch_hub_connector(name, timeout=timeout)
+        if conn_data:
+            connectors.append(conn_data)
+        else:
+            connectors.append({
+                "key": name,
+                "title": name.replace("_", " ").title(),
+                "install_hint": f"pip install streamwright-{name.replace('_', '-')}"
+            })
+
+    return connectors

streamwright_mcp/inspector.py

@@ -0,0 +1,170 @@
+"""
+Stream transformation and SQL inspection engine for StreamWright MCP.
+
+Analyzes pipeline stream configurations, requests, DuckDB SQL transform steps,
+and export definitions.
+"""
+
+import os
+import re
+from typing import Any, Dict, List, Optional
+
+from streamwright.core.config.loader import load_source
+
+_TABLE_REF = re.compile(r"\bFROM\s+([A-Za-z_][A-Za-z0-9_]*)\b|\bJOIN\s+([A-Za-z_][A-Za-z0-9_]*)\b", re.IGNORECASE)
+
+
+def _extract_sql_sources(sql: str) -> List[str]:
+    """Extracts table names referenced in FROM or JOIN clauses."""
+    sources = set()
+    for match in _TABLE_REF.finditer(sql):
+        t1, t2 = match.groups()
+        table = t1 or t2
+        if table:
+            sources.add(table)
+    return sorted(list(sources))
+
+
+def inspect_stream_transform(source_dir: str, stream_name: str) -> Dict[str, Any]:
+    """
+    Parses and inspects a specific stream's requests, SQL transformations, and exports.
+
+    Args:
+        source_dir: Absolute or relative path to the source directory.
+        stream_name: Name of the stream to inspect.
+
+    Returns:
+        Structured breakdown of the stream's execution plan.
+    """
+    abs_path = os.path.abspath(os.path.expanduser(source_dir))
+    if not os.path.exists(abs_path):
+        return {
+            "found": False,
+            "error": f"Source directory '{source_dir}' does not exist.",
+        }
+
+    try:
+        source_data = load_source(abs_path)
+    except Exception as exc:
+        return {
+            "found": False,
+            "error": f"Failed to load source at '{source_dir}': {exc}",
+        }
+
+    streams = source_data.get("streams", [])
+    matched_stream: Optional[Dict[str, Any]] = None
+    all_stream_names = []
+
+    for s in streams:
+        name = s.get("name")
+        if name:
+            all_stream_names.append(name)
+            if name == stream_name:
+                matched_stream = s
+
+    if not matched_stream:
+        return {
+            "found": False,
+            "stream_name": stream_name,
+            "error": f"Stream '{stream_name}' not found in source '{abs_path}'.",
+            "available_streams": all_stream_names,
+        }
+
+    # Analyze requests
+    raw_requests = matched_stream.get("requests", [])
+    parsed_requests = []
+    request_names = set()
+    for req in raw_requests:
+        req_name = req.get("name")
+        if req_name:
+            request_names.add(req_name)
+        if "http" in req:
+            http_spec = req.get("http", {})
+            parsed_requests.append({
+                "name": req_name,
+                "kind": "http",
+                "method": http_spec.get("method", "GET"),
+                "path": http_spec.get("path"),
+                "params": http_spec.get("params"),
+            })
+        elif "sdk" in req:
+            parsed_requests.append({
+                "name": req_name,
+                "kind": "sdk",
+                "sdk": req.get("sdk"),
+                "service": req.get("service"),
+                "method": req.get("method"),
+                "arguments": req.get("arguments"),
+            })
+        else:
+            parsed_requests.append({
+                "name": req_name,
+                "kind": "custom",
+                "spec": req,
+            })
+
+    # Analyze transform steps
+    transform_block = matched_stream.get("transform", {})
+    mode = transform_block.get("mode", "page")
+    steps = transform_block.get("steps", [])
+
+    # If steps is not in transform dict (e.g. shorthand transform: [...])
+    if isinstance(transform_block, list):
+        steps = transform_block
+        mode = "page"
+
+    parsed_steps = []
+    for step in steps:
+        step_name = step.get("name")
+        select_sql = step.get("select", "").strip()
+        referenced_tables = _extract_sql_sources(select_sql)
+
+        # Distinguish whether input is a raw request table or intermediate step
+        inputs = []
+        for ref in referenced_tables:
+            if ref in request_names:
+                inputs.append({"name": ref, "type": "request"})
+            else:
+                inputs.append({"name": ref, "type": "step_or_table"})
+
+        parsed_steps.append({
+            "name": step_name,
+            "description": step.get("description"),
+            "select_sql": select_sql,
+            "inputs": inputs,
+        })
+
+    # Analyze exports
+    exports_block = matched_stream.get("export", {})
+    parsed_exports = []
+    if isinstance(exports_block, dict):
+        for exp_name, exp_cfg in exports_block.items():
+            if isinstance(exp_cfg, dict):
+                parsed_exports.append({
+                    "name": exp_name,
+                    "step": exp_cfg.get("step"),
+                    "primary_key": exp_cfg.get("primary_key", []),
+                    "description": exp_cfg.get("description"),
+                })
+            elif isinstance(exp_cfg, str):
+                parsed_exports.append({
+                    "name": exp_name,
+                    "step": exp_cfg,
+                    "primary_key": [],
+                })
+
+    return {
+        "found": True,
+        "stream_name": stream_name,
+        "source_name": source_data.get("name"),
+        "description": matched_stream.get("description"),
+        "partitions": matched_stream.get("partitions"),
+        "incremental": matched_stream.get("incremental"),
+        "requests": parsed_requests,
+        "transform": {
+            "mode": mode,
+            "step_count": len(parsed_steps),
+            "steps": parsed_steps,
+        },
+        "exports": parsed_exports,
+    }

streamwright_mcp/server.py

@@ -0,0 +1,153 @@
+"""
+StreamWright Model Context Protocol (MCP) Server.
+
+Exposes programmatic tools and resources for inspecting connector contracts,
+core schemas, source validation, and transform analysis without file duplication.
+"""
+
+import json
+from typing import Any, Dict, List, Optional
+
+try:
+    from mcp.server.mcpserver import MCPServer
+except ImportError:
+    from mcp.server.fastmcp import FastMCP as MCPServer
+
+from streamwright_mcp.contracts import (
+    get_cli_reference as _get_cli_reference,
+    get_connector_contract as _get_contract,
+    get_core_schema as _get_schema,
+    list_installed_connectors,
+)
+from streamwright_mcp.hub import list_hub_connectors
+from streamwright_mcp.inspector import inspect_stream_transform as _inspect_transform
+from streamwright_mcp.validator import validate_source_config as _validate_source
+
+server = MCPServer("streamwright-mcp")
+
+
+@server.tool()
+def list_connectors(include_hub: bool = False) -> List[Dict[str, Any]]:
+    """
+    Lists StreamWright connectors.
+
+    Args:
+        include_hub: If True, also includes uninstalled connectors available in the StreamWright Hub registry.
+
+    Returns:
+        List of connector summaries containing name, title, category, transport, and installation status.
+    """
+    installed = list_installed_connectors()
+    if not include_hub:
+        return installed
+
+    installed_names = {c["name"] for c in installed}
+    hub_connectors = list_hub_connectors()
+
+    results = list(installed)
+    for h in hub_connectors:
+        key = h.get("key")
+        if key and key not in installed_names:
+            results.append({
+                "name": key,
+                "title": h.get("title", key.replace("_", " ").title()),
+                "category": h.get("family", "hub"),
+                "transport": "unknown",
+                "version": None,
+                "installed": False,
+                "install_hint": h.get("install_hint", f"pip install streamwright-{key.replace('_', '-')}"),
+            })
+
+    results.sort(key=lambda x: x["name"])
+    return results
+
+
+@server.tool()
+def get_connector_contract(name: str) -> Dict[str, Any]:
+    """
+    Retrieves the complete in-code contract for a StreamWright connector.
+
+    Returns the 5-part specification:
+    1. source.yaml contract snippet
+    2. streams/<stream>.yaml contract snippet
+    3. Authentication & secrets requirements
+    4. Transform & DuckDB SQL data shaping
+    5. Execution & runtime behaviors (transport, pagination, retries)
+
+    If the connector is not installed locally, returns the installation command.
+
+    Args:
+        name: Name of the connector (e.g. 's3', 'postgres', 'restapi', 'google_ads', 'openai_ads').
+    """
+    return _get_contract(name)
+
+
+@server.tool()
+def get_core_schema(kind: str = "all") -> Dict[str, Any]:
+    """
+    Returns the formal Draft 7 JSON schema and declarative DSL specification for StreamWright.
+
+    Args:
+        kind: 'source' (source.yaml schema), 'stream' (streams/*.yaml schema), or 'all' (both schemas plus full DSL documentation).
+    """
+    return _get_schema(kind)
+
+
+@server.tool()
+def validate_source_config(source_dir: str) -> Dict[str, Any]:
+    """
+    Performs static validation on a StreamWright source folder (source.yaml and streams/*.yaml).
+
+    Checks YAML structure, keys, credentials, Jinja references, DuckDB SQL transforms,
+    and export consistency with pinpoint file:line diagnostics.
+
+    Args:
+        source_dir: Absolute or relative path to the source directory.
+    """
+    return _validate_source(source_dir)
+
+
+@server.tool()
+def inspect_stream_transform(source_dir: str, stream_name: str) -> Dict[str, Any]:
+    """
+    Parses and explains the requests, DuckDB SQL transform steps, table inputs,
+    and export contracts for a specific stream.
+
+    Args:
+        source_dir: Path to the pipeline source directory.
+        stream_name: Name of the stream to inspect.
+    """
+    return _inspect_transform(source_dir, stream_name)
+
+
+@server.tool()
+def get_cli_reference(command: Optional[str] = None) -> Dict[str, Any]:
+    """
+    Guides the AI assistant on how to inspect, discover, and run StreamWright CLI commands.
+    Directs the LLM to run and inspect `sw --help` or `sw <subcommand> --help` directly in the user's workspace.
+
+    Args:
+        command: Optional subcommand to inspect ('run', 'validate', 'connectors', 'mcp').
+    """
+    return _get_cli_reference(command)
+
+
+# Resources
+@server.resource("streamwright://schema/source")
+def source_schema_resource() -> str:
+    """JSON Schema (Draft 7) for StreamWright source.yaml."""
+    schema_dict = _get_schema("source").get("source_schema", {})
+    return json.dumps(schema_dict, indent=2)
+
+
+@server.resource("streamwright://schema/stream")
+def stream_schema_resource() -> str:
+    """JSON Schema (Draft 7) for StreamWright streams/<stream>.yaml."""
+    schema_dict = _get_schema("stream").get("stream_schema", {})
+    return json.dumps(schema_dict, indent=2)
+
+
+@server.resource("streamwright://schema/core")
+def core_dsl_resource() -> str:
+    """Complete markdown specification contract of the StreamWright DSL."""
+    return _get_schema("all").get("dsl_specification", "")

streamwright_mcp/validator.py

@@ -0,0 +1,99 @@
+"""
+Source configuration validation wrapper for StreamWright MCP.
+
+Validates StreamWright source directories without executing them,
+returning structured file-and-line diagnostics.
+"""
+
+import os
+from typing import Any, Dict, List
+
+from streamwright.core.validation.engine import validate_source
+
+
+def validate_source_config(source_dir: str) -> Dict[str, Any]:
+    """
+    Validates a StreamWright source folder (source.yaml and streams/*.yaml).
+
+    Args:
+        source_dir: Absolute or relative path to the source directory.
+
+    Returns:
+        Structured diagnostic dictionary with valid status, error count, warning count,
+        and list of issue items.
+    """
+    abs_path = os.path.abspath(os.path.expanduser(source_dir))
+    if not os.path.exists(abs_path):
+        return {
+            "valid": False,
+            "error_count": 1,
+            "warning_count": 0,
+            "errors": [{
+                "severity": "error",
+                "code": "not-found",
+                "message": f"Source directory '{source_dir}' does not exist.",
+                "file": source_dir,
+                "line": None,
+                "column": None,
+                "path": "",
+            }],
+            "warnings": [],
+            "summary": f"Failed: Directory '{source_dir}' does not exist.",
+        }
+
+    try:
+        issues = validate_source(abs_path)
+    except Exception as exc:
+        return {
+            "valid": False,
+            "error_count": 1,
+            "warning_count": 0,
+            "errors": [{
+                "severity": "error",
+                "code": "validator-exception",
+                "message": str(exc),
+                "file": source_dir,
+                "line": None,
+                "column": None,
+                "path": "",
+            }],
+            "warnings": [],
+            "summary": f"Validation failed with exception: {exc}",
+        }
+
+    errors: List[Dict[str, Any]] = []
+    warnings: List[Dict[str, Any]] = []
+
+    for issue in issues:
+        item = {
+            "severity": issue.severity,
+            "code": getattr(issue, "code", ""),
+            "message": issue.message,
+            "file": getattr(issue, "file", None),
+            "line": getattr(issue, "line", None),
+            "column": getattr(issue, "column", None),
+            "path": getattr(issue, "path", ""),
+        }
+        if issue.severity == "error":
+            errors.append(item)
+        else:
+            warnings.append(item)
+
+    is_valid = len(errors) == 0
+    if is_valid:
+        if len(warnings) == 0:
+            summary = f"Valid: Source '{os.path.basename(abs_path)}' has no errors or warnings."
+        else:
+            summary = f"Valid with warnings: Source '{os.path.basename(abs_path)}' has {len(warnings)} warning(s)."
+    else:
+        summary = f"Invalid: Source '{os.path.basename(abs_path)}' has {len(errors)} error(s) and {len(warnings)} warning(s)."
+
+    return {
+        "valid": is_valid,
+        "source_path": abs_path,
+        "error_count": len(errors),
+        "warning_count": len(warnings),
+        "errors": errors,
+        "warnings": warnings,
+        "summary": summary,
+    }

streamwright_mcp-0.0.1.dist-info/METADATA

@@ -0,0 +1,153 @@
+Metadata-Version: 2.4
+Name: streamwright-mcp
+Version: 0.0.1
+Summary: Model Context Protocol (MCP) server for StreamWright declarative ELT framework
+Author: Karthick Jaganathan
+License: Apache-2.0
+Project-URL: Homepage, https://streamwright.web.app
+Project-URL: Documentation, https://streamwright.web.app/docs/ai/mcp
+Project-URL: Repository, https://github.com/karthick-jaganathan/streamwright-mcp
+Project-URL: Issue Tracker, https://github.com/karthick-jaganathan/streamwright-mcp/issues
+Requires-Python: >=3.10
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: mcp>=1.0.0
+Requires-Dist: streamwright>=0.1.0
+Requires-Dist: pyyaml>=6.0.0
+Requires-Dist: pydantic>=2.0.0
+Requires-Dist: requests>=2.25.0
+Provides-Extra: test
+Requires-Dist: pytest>=8.0.0; extra == "test"
+Dynamic: license-file
+
+# StreamWright MCP Server
+
+[![PyPI version](https://img.shields.io/pypi/v/streamwright-mcp.svg)](https://pypi.org/project/streamwright-mcp/)
+[![License](https://img.shields.io/badge/License-Apache%202.0-blue.svg)](https://opensource.org/licenses/Apache-2.0)
+[![Python](https://img.shields.io/badge/python-3.10+-blue.svg)](https://www.python.org/downloads/)
+
+**StreamWright MCP** is the official [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server for [StreamWright](https://streamwright.web.app), the declarative data integration and ELT framework.
+
+It allows AI coding assistants (such as Claude Desktop, Cursor, Google Antigravity, GitHub Copilot, and Zed) to inspect installed connectors, query Draft-7 pipeline schemas, validate YAML sources with pinpoint error locations, and analyze DuckDB SQL transform pipelines in real time — eliminating hallucinations when building data pipelines.
+
+---
+
+## Key Capabilities
+
+- **In-Code Connector Contracts**: Introspects installed connector packages (`restapi`, `postgres`, `s3`, etc.) directly from Python entry points to extract live contracts, authentication specs, and transport behaviors without static copies.
+- **Hub Discovery**: Discovers uninstalled connectors from the StreamWright Hub registry and provides instant installation recipes.
+- **Static Pipeline Validation**: Validates `source.yaml` and `streams/*.yaml` pipelines before execution, returning structured diagnostics with file, line, and column locations.
+- **SQL Transform Inspection**: Parses and traces multi-step DuckDB SQL transformations, table dependencies, and export formats for any stream.
+- **Core DSL Schemas**: Exposes authoritative Draft-7 JSON schemas for editor autocomplete, linting, and LLM grounding.
+- **CLI Guidance**: Steers AI agents to explore live CLI commands (`sw run`, `sw validate`, `sw connectors`, `sw mcp`) in the local workspace.
+
+---
+
+## Installation
+
+Install via `pip`:
+
+```bash
+pip install streamwright-mcp
+```
+
+Or using `uv`:
+
+```bash
+uv pip install streamwright-mcp
+```
+
+---
+
+## Configuration
+
+Add `streamwright-mcp` to your MCP client configuration file (e.g., `claude_desktop_config.json`, `mcp.json`, or Antigravity's `mcp_config.json`).
+
+### Standard Configuration
+
+```json
+{
+  "mcpServers": {
+    "streamwright": {
+      "command": "streamwright-mcp"
+    }
+  }
+}
+```
+
+### Using StreamWright CLI Shorthand (`sw`)
+
+If you have `streamwright` installed, you can launch the MCP server directly via `sw mcp`:
+
+```json
+{
+  "mcpServers": {
+    "streamwright": {
+      "command": "sw",
+      "args": ["mcp"]
+    }
+  }
+}
+```
+
+### Ephemeral Execution (`uvx`)
+
+Run on-demand without installing into your global environment:
+
+```json
+{
+  "mcpServers": {
+    "streamwright": {
+      "command": "uvx",
+      "args": ["streamwright-mcp"]
+    }
+  }
+}
+```
+
+---
+
+## Usage
+
+### Starting the Server
+
+The server runs over standard input/output (`stdio`) by default:
+
+```bash
+streamwright-mcp
+```
+
+You can also specify transport options:
+
+```bash
+# stdio (default)
+streamwright-mcp --transport stdio
+
+# Server-Sent Events (SSE)
+streamwright-mcp --transport sse
+```
+
+Or run as a Python module:
+
+```bash
+python -m streamwright_mcp.cli
+```
+
+---
+
+## Resources
+
+MCP clients that support resource attachments can access:
+
+- `streamwright://schema/source` — JSON Schema (Draft 7) for `source.yaml`.
+- `streamwright://schema/stream` — JSON Schema (Draft 7) for `streams/<stream>.yaml`.
+- `streamwright://schema/core` — Full Markdown specification of the StreamWright DSL.
+
+---
+
+## Documentation & Ecosystem
+
+- **Documentation**: https://streamwright.web.app
+- **MCP Guide**: https://streamwright.web.app/docs/ai/mcp
+- **Core Package**: https://pypi.org/project/streamwright/
+- **Repository**: https://github.com/karthick-jaganathan/streamwright-mcp

streamwright_mcp-0.0.1.dist-info/RECORD

@@ -0,0 +1,13 @@
+streamwright_mcp/__init__.py,sha256=4iy6InZKBEQcI0Sre-bWVxxmR0EmSU37nhEDBsQNb9c,81
+streamwright_mcp/cli.py,sha256=mOTdnhrzyFuGqPMK-VKQegOG5LLhiHAXZVAkEVMdliY,576
+streamwright_mcp/contracts.py,sha256=qQApBEycwH0NwmRZUNaXbQX58hoWo5amg7GIeAciY9k,8347
+streamwright_mcp/hub.py,sha256=ldWZ5Tb9ZrZ-Cp82DNvy-7GUJl64qIPRrL7x9yjE2qw,3235
+streamwright_mcp/inspector.py,sha256=hCZKYcDsSglds7azSQV8urBEQn19RQq8BKN1Q10LPWo,5536
+streamwright_mcp/server.py,sha256=G0vE6kdZcmzCPjZXD4I-oXrdwfXpb5RMHJnTHHC6LKc,5170
+streamwright_mcp/validator.py,sha256=FJDFr5FUiy0pnT_qHvGqueFB6V0g5Py-kT32FnYJ8ps,3157
+streamwright_mcp-0.0.1.dist-info/licenses/LICENSE,sha256=xx0jnfkXJvxRnG63LTGOxlggYnIysveWIZ6H3PNdCrQ,11357
+streamwright_mcp-0.0.1.dist-info/METADATA,sha256=t25SwHapgNWL7sHaLuYHhrUdK3JL0QrzTmD518ile0Y,4624
+streamwright_mcp-0.0.1.dist-info/WHEEL,sha256=YVMoNqKzERt-wjUZwJ33xBGAwnFl-4cqbYkTtWa4itE,91
+streamwright_mcp-0.0.1.dist-info/entry_points.txt,sha256=LCT4J74-VDi5SUqiaWothyCTwALVnFP3VjQ_1MvtcTM,63
+streamwright_mcp-0.0.1.dist-info/top_level.txt,sha256=S6_BYHDMgKEhYjH48h_PHmFjPCxN9BkzLX1fRhZKm1I,17
+streamwright_mcp-0.0.1.dist-info/RECORD,,

streamwright_mcp-0.0.1.dist-info/WHEEL

@@ -0,0 +1,5 @@
+Wheel-Version: 1.0
+Generator: setuptools (84.0.0)
+Root-Is-Purelib: true
+Tag: py3-none-any
+

streamwright_mcp-0.0.1.dist-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+streamwright-mcp = streamwright_mcp.cli:main

streamwright_mcp-0.0.1.dist-info/licenses/LICENSE

@@ -0,0 +1,201 @@
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright [yyyy] [name of copyright owner]
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

streamwright_mcp-0.0.1.dist-info/top_level.txt

@@ -0,0 +1 @@
+streamwright_mcp