PyPI - everyrow-mcp - Versions diffs - 0.1.10__tar.gz → 0.2.0__tar.gz - Mend

everyrow-mcp 0.1.10tar.gz → 0.2.0tar.gz

This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.

Files changed (16) hide show

{everyrow_mcp-0.1.10 → everyrow_mcp-0.2.0}/.gitignore RENAMED Viewed

@@ -223,3 +223,6 @@ __marimo__/
 # MCP registry tokens
 .mcpregistry_*
+# Claude Code local instructions
+CLAUDE.local.md

{everyrow_mcp-0.1.10 → everyrow_mcp-0.2.0}/PKG-INFO RENAMED Viewed

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: everyrow-mcp
-Version: 0.1.10
+Version: 0.2.0
 Summary: MCP server for everyrow: agent ops at spreadsheet scale
 Requires-Python: >=3.12
 Requires-Dist: everyrow>=0.1.5
@@ -19,17 +19,25 @@ This server exposes everyrow's 5 core operations as MCP tools, allowing LLM appl
 ## Installation
+The server requires an everyrow API key. Get one at [everyrow.io/api-key](https://everyrow.io/api-key) ($20 free credit).
 ### Claude Desktop
 Download the latest `.mcpb` bundle from the [GitHub Releases](https://github.com/futuresearch/everyrow-sdk/releases) page and double-click to install in Claude Desktop. You'll be prompted to enter your everyrow API key during setup.
 > **Note:** The MCPB bundle works in Claude Desktop's **Chat** mode. Due to a [known limitation](https://github.com/anthropics/claude-code/issues/20377), local MCP servers are not currently exposed in Cowork mode.
-### Manual Config
+### Cursor
+Set the environment variable in your terminal shell before opening cursor. You may need to re-open cursor from your shell after this. Alternatively, hardcode the api key within cursor settings instead of the hard-coded `${env:EVERYROW_API_KEY}`
+```bash
+export EVERYROW_API_KEY=your_key_here
+```
-The server requires an everyrow API key. Get one at [everyrow.io/api-key](https://everyrow.io/api-key) ($20 free credit).
+[![Install MCP Server](https://cursor.com/deeplink/mcp-install-dark.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=everyrow&config=eyJlbnYiOnsiRVZFUllST1dfQVBJX0tFWSI6IiR7ZW52OkVWRVJZUk9XX0FQSV9LRVl9In0sImNvbW1hbmQiOiJ1dnggZXZlcnlyb3ctbWNwIn0%3D)
+### Manual Config
-Either set the API key in your shell environment, or hardcode it directly in the config below.
+Either set the API key in your shell environment as mentioned above, or hardcode it directly in the config below. Environment variable interpolation may differ between MCP clients.
 ```bash
 export EVERYROW_API_KEY=your_key_here

{everyrow_mcp-0.1.10 → everyrow_mcp-0.2.0}/README.md RENAMED Viewed

@@ -8,17 +8,25 @@ This server exposes everyrow's 5 core operations as MCP tools, allowing LLM appl
 ## Installation
+The server requires an everyrow API key. Get one at [everyrow.io/api-key](https://everyrow.io/api-key) ($20 free credit).
 ### Claude Desktop
 Download the latest `.mcpb` bundle from the [GitHub Releases](https://github.com/futuresearch/everyrow-sdk/releases) page and double-click to install in Claude Desktop. You'll be prompted to enter your everyrow API key during setup.
 > **Note:** The MCPB bundle works in Claude Desktop's **Chat** mode. Due to a [known limitation](https://github.com/anthropics/claude-code/issues/20377), local MCP servers are not currently exposed in Cowork mode.
-### Manual Config
+### Cursor
+Set the environment variable in your terminal shell before opening cursor. You may need to re-open cursor from your shell after this. Alternatively, hardcode the api key within cursor settings instead of the hard-coded `${env:EVERYROW_API_KEY}`
+```bash
+export EVERYROW_API_KEY=your_key_here
+```
-The server requires an everyrow API key. Get one at [everyrow.io/api-key](https://everyrow.io/api-key) ($20 free credit).
+[![Install MCP Server](https://cursor.com/deeplink/mcp-install-dark.svg)](cursor://anysphere.cursor-deeplink/mcp/install?name=everyrow&config=eyJlbnYiOnsiRVZFUllST1dfQVBJX0tFWSI6IiR7ZW52OkVWRVJZUk9XX0FQSV9LRVl9In0sImNvbW1hbmQiOiJ1dnggZXZlcnlyb3ctbWNwIn0%3D)
+### Manual Config
-Either set the API key in your shell environment, or hardcode it directly in the config below.
+Either set the API key in your shell environment as mentioned above, or hardcode it directly in the config below. Environment variable interpolation may differ between MCP clients.
 ```bash
 export EVERYROW_API_KEY=your_key_here

{everyrow_mcp-0.1.10 → everyrow_mcp-0.2.0}/manifest.json RENAMED Viewed

@@ -2,7 +2,7 @@
   "manifest_version": "0.4",
   "name": "everyrow-mcp",
   "display_name": "Everyrow MCP Server",
-  "version": "0.1.10",
+  "version": "0.2.0",
   "description": "AI-powered dataframe ops: transform, dedupe, merge, rank, and screen with natural language",
   "long_description": "MCP server for everyrow: agent ops at spreadsheet scale. This server exposes everyrow's 5 core operations as MCP tools, allowing LLM applications to screen, rank, dedupe, merge, and run agents on CSV files. All tools operate on local CSV files.",
   "author": {

{everyrow_mcp-0.1.10 → everyrow_mcp-0.2.0}/pyproject.toml RENAMED Viewed

@@ -1,6 +1,6 @@
 [project]
 name = "everyrow-mcp"
-version = "0.1.10"
+version = "0.2.0"
 description = "MCP server for everyrow: agent ops at spreadsheet scale"
 readme = "README.md"
 requires-python = ">=3.12"

{everyrow_mcp-0.1.10 → everyrow_mcp-0.2.0}/server.json RENAMED Viewed

@@ -9,13 +9,13 @@
     "subfolder": "everyrow-mcp"
   },
   "websiteUrl": "https://github.com/futuresearch/everyrow-sdk/tree/main/everyrow-mcp",
-  "version": "0.1.10",
+  "version": "0.2.0",
   "packages": [
     {
       "registryType": "pypi",
       "registryBaseUrl": "https://pypi.org",
       "identifier": "everyrow-mcp",
-      "version": "0.1.10",
+      "version": "0.2.0",
       "runtimeHint": "uvx",
       "transport": {
         "type": "stdio"

{everyrow_mcp-0.1.10 → everyrow_mcp-0.2.0}/src/everyrow_mcp/server.py RENAMED Viewed

@@ -5,7 +5,7 @@ import logging
 import os
 import sys
 from contextlib import asynccontextmanager
-from typing import Any
+from typing import Any, Literal
 import pandas as pd
 from everyrow.api_utils import create_client
@@ -354,6 +354,10 @@ class MergeInput(BaseModel):
         description="Optional column name in the right table to use as the merge key. "
         "If not provided, the LLM will determine the best matching strategy.",
     )
+    use_web_search: Literal["auto", "yes", "no"] | None = Field(
+        default=None,
+        description='Optional. Control web search behavior: "auto" tries LLM merge first then conditionally searches, "no" skips web search entirely, "yes" forces web search on every row. Defaults to "auto" if not provided.',
+    )
     @field_validator("left_csv", "right_csv")
     @classmethod
@@ -395,6 +399,7 @@ async def everyrow_merge(params: MergeInput) -> str:
         right_table=right_df,
         merge_on_left=params.merge_on_left,
         merge_on_right=params.merge_on_right,
+        use_web_search=params.use_web_search,
     )
     output_file = resolve_output_path(params.output_path, params.left_csv, "merged")