This server enables fast, system-wide file and folder search on Windows by leveraging the voidtools Everything index engine, providing two tools: search and status.
search: Perform powerful queries across your system using the Everything index.
Supports wildcards (*, ?), operators, and filters (e.g., ext:cs, path:D:\source)
Filter results to files only or folders only
Enable case-sensitive matching with match_case
Match against the full path instead of just the filename with match_path
Limit searches to a specific folder subtree using scope_path
Control result count (default 100, max 1000) via max_results
Returns results as JSON
status: Check the health and availability of the server's dependencies, including the Everything SDK DLL, the Everything tray client (Everything.exe), and the resolved es.exe CLI path.
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., "@@quickerhub/everything-mcp find all .cs files under D:\source\repos"
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.
Fast cross-project file search for AI agents via voidtools Everything on Windows.
Uses the Everything SDK DLL (same approach as QuickerPc), not es.exe.
Published by QuickerHub.
Cursor / Claude / VS Code
→ everything-mcp.exe (MCP stdio)
→ Everything64.dll (bundled SDK IPC client)
→ Everything.exe (user-installed tray client + index engine)The bundled DLL is only an IPC client. Everything.exe must be installed and running to maintain the file index.
Related MCP server: everything-search-mcp
Windows x64
Everything 1.4.x installed (stable). Tray client should be running.
Node.js 18+ (only for npx launcher)
No es.exe / ES CLI required.
{
"mcpServers": {
"everything-search": {
"command": "D:\\source\\repos\\quicker\\everything-mcp\\publish\\cli\\everything-mcp.exe",
"args": []
}
}
}Build first:
cd D:\source\repos\quicker\everything-mcp
.\build.ps1 -Publish{
"mcpServers": {
"everything-search": {
"command": "npx",
"args": ["-y", "@quickerhub/everything-mcp"]
}
}
}Override exe path:
{
"env": {
"EVERYTHING_MCP_EXE": "D:\\path\\to\\everything-mcp.exe"
}
}Tool | Description |
| Search files/folders via Everything index (returns JSON) |
| Check bundled SDK DLL and Everything client state |
search parametersParameter | Description |
| Everything query ( |
| Default 100, max 1000 |
| Limit to folder subtree |
| Match full path |
| Case-sensitive |
| Whole words only |
| Regex mode |
|
|
| Try starting Everything tray client (default true) |
{
"query": "quicker-rpc",
"scope_path": "D:\\source\\repos\\quicker",
"max_results": 20
}.\build.ps1 # build only
.\build.ps1 -Publish # publish to publish/cli
.\publish\cli\everything-mcp.exe --smoke-testLatest: https://github.com/QuickerHub/everything-mcp/releases/latest
.\publish\Publish-GitHubRelease.ps1 -Version 0.2.0
gh release create v0.2.0 --title "v0.2.0" artifacts/*@quickerhub/everything-mcp)Requires NPM_TOKEN repo secret (npm automation token with publish access to @quickerhub).
gh secret set NPM_TOKEN --repo QuickerHub/everything-mcp
gh workflow run publish.yml --repo QuickerHub/everything-mcp -f version=0.2.0Creating a GitHub Release also triggers the npm publish workflow automatically.
QuickerPc | everything-mcp | |
SDK DLL |
| same |
Everything.exe | user-installed, required | same |
IPC | P/Invoke | P/Invoke |
es.exe | not used | not used |
MIT. Everything SDK DLL is from voidtools (public SDK); not affiliated with voidtools.
Search files and folders across the system using voidtools Everything index. Ideal for cross-project path discovery.
| Name | Required | Description | Default |
|---|---|---|---|
| query | Yes | Everything search query. Supports wildcards (*, ?), operators, and filters like ext:cs path:D:\source\repos | |
| max_results | No | Maximum number of results (default 100, max 1000) | |
| scope_path | No | Limit search to this folder and its subfolders | |
| match_path | No | Match against full path instead of filename only | |
| match_case | No | Case-sensitive search | |
| files_only | No | Return files only | |
| folders_only | No | Return folders only |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
The description mentions the use of an external index ('using voidtools Everything index'), which is a behavioral trait. However, it does not disclose whether the operation is read-only, what happens if the index is unavailable, or any required permissions. Without annotations, the description carries the full burden but provides only partial transparency.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is exceptionally concise with two sentences. The first sentence defines the tool's core functionality, and the second provides a typical use case. No waste or redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Despite having 7 parameters and no output schema, the description adequately covers the tool's purpose, scope, and typical usage. It lacks details on return format or error handling, but the schema descriptions for parameters compensate. The description is sufficient for understanding the tool's role within the system.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The input schema has 100% description coverage for all parameters, so baseline is 3. The tool description does not add any additional semantic meaning beyond what the schema already provides, such as explaining how parameters interact or providing usage examples.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Search' and resource 'files and folders across the system', and uniquely identifies the tool via 'voidtools Everything index'. It clearly distinguishes from the sibling 'status', which is not a search tool.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides a clear use case ('Ideal for cross-project path discovery'), but does not explicitly state when not to use this tool or mention alternatives. It gives enough context to infer appropriate usage.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Check Everything CLI availability and resolved es.exe path
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations, the description carries the full burden. While it indicates a read-only status check, it does not disclose error behavior or side effects. It is minimal but not misleading.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is a single sentence that is direct and free of extraneous words. Every part of the description earns its place.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple status tool, the description covers the main purpose. However, it lacks details about return values or how to interpret results. With no output schema, more context would improve completeness.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has no parameters, so the schema coverage is 100%. The description adds no parameter information, which is acceptable given there are none to document. Baseline 4 for zero parameters.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses a specific verb 'Check' and clearly identifies the resource 'Everything CLI availability and resolved es.exe path'. It distinguishes from the sibling tool 'search' which performs a different function.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
No guidance is provided on when to use this tool versus the sibling 'search'. The description simply states what it does without context for appropriate use cases or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
v0.1.0searchstatusScored across 2 tools
The two tools have completely distinct purposes: one for searching files, one for checking service status. No overlap or ambiguity.
Both tools use a consistent single-word verb pattern ('search', 'status'), clear and predictable.
With only two tools, the server feels thin for a search utility, but it might be sufficient for a minimal integration. Borderline between too few and acceptable.
Missing many expected search capabilities like path exclusions, indexing control, or advanced filters. The surface is incomplete for a robust search tool.
Securely search and manage workspace context files for AI agents and teams.
Agent-driven search: build, import, tune, search, and score result quality — all over MCP.
Agentic search over your Dewey document collections from any MCP-compatible client.
Code intelligence for coding agents: semantic, AST, graph, and full-text search. 279+ languages.
