Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Ressl AI MCP Server search for 'function' in my project's main.js file"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
MCP server for file search functionality with support for both partial and exact word matching.
Partial Keyword Search: Find all occurrences of a keyword including partial matches
Exact Word Search: Match complete words only with optional case sensitivity
Detailed Results: Line numbers, column positions, and matched text for all occurrences
MCP Inspector Integration: Built-in support for testing with MCP Inspector
Related MCP server: MCP Keyword Search
npm installnpm run buildnpm startThis will automatically build the project and launch the MCP Inspector for testing.
npm run devRuns TypeScript compiler in watch mode for continuous development.
Searches for a keyword within a file, finding all occurrences including partial matches.
Parameters:
filePath (string, required): Path to the file to search in
keyword (string, required): Keyword to search for
Example:
{
"filePath": "./sample.txt",
"keyword": "search"
}Result: Finds "search", "searching", "researcher", etc.
Searches for exact word matches within a file using word boundaries.
Parameters:
filePath (string, required): Path to the file to search in
word (string, required): Exact word to search for
caseSensitive (boolean, optional): Whether search should be case sensitive (default: false)
Example:
{
"filePath": "./sample.txt",
"word": "search",
"caseSensitive": false
}Result: Finds only exact "search" matches, not "searching" or "researcher"
A sample.txt file is included in the project for testing purposes.
Search Term | Tool | Matches in "searching" |
"search" | search_in_file | Yes (partial match) |
"search" | exact_word_search | No (exact word only) |
"AI" | search_in_file | Yes (finds "Ressl AI" and "AIR") |
"AI" | exact_word_search | Only "Ressl AI" (not "AIR") |
Run npm start to launch the inspector
Open the provided URL in your browser
Select a tool from the Tools tab
Enter the required parameters
Click Execute to see results
Search for an exact word match within a specified file. Only matches complete words, not partial matches.
Inputs: filePath (required), word (required), caseSensitive.
Search for a keyword within a specified file. Finds all occurrences including partial matches.
Inputs: filePath (required), keyword (required).
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 2 tools
The two tools have overlapping purposes, both searching within files, with only subtle differences in matching behavior (exact word vs. keyword with partial matches). This creates ambiguity, as an agent might struggle to choose between them without understanding the nuanced distinction, and they could easily be confused for similar tasks.
The tool names follow a consistent snake_case pattern (exact_word_search, search_in_file) and use clear verbs ('search'), which aids readability. However, the naming is not perfectly consistent, as one specifies 'exact_word' while the other uses 'in_file', but overall, the pattern is predictable and coherent.
With only 2 tools, the server feels thin and under-scoped for a general-purpose AI MCP server, suggesting limited functionality. This low count may not adequately cover the domain implied by the server name, potentially leaving gaps in capabilities and making it less useful for agents.
Inferred as a file search domain, the tool set is severely incomplete, lacking basic operations like listing files, reading file contents, or handling multiple files. The two tools only cover specific search variations, leaving significant gaps that will likely cause agent failures in broader tasks.
Read and search folders on your own computer with explicit consent. Files are never uploaded.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
Search the source code (HTML, JavaScript, CSS) of web pages.
Securely search and manage workspace context files for AI agents and teams.