Everything Search MCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| EVERYTHING_URL | No | Everything HTTP server URL (e.g. `http://127.0.0.1:17603/`). When set, uses HTTP transport instead of IPC. | |
| EVERYTHING_ES_PATH | No | Custom path to `es.exe`. | bundled |
| EVERYTHING_INSTANCE | No | Probes the default instance, `1.5a`, and `1.5`. Set this for a custom instance; `""` selects the default instance. | |
| EVERYTHING_PASSWORD | No | Basic auth password for HTTP server. | |
| EVERYTHING_USERNAME | No | Basic auth username for HTTP server. | |
| EVERYTHING_TIMEOUT_MS | No | Query timeout in milliseconds (100–120000). | 15000 |
| EVERYTHING_MAX_RESULTS | No | Row cap for each query and the whole batch (1–1000). | 1000 |
| EVERYTHING_OUTPUT_BYTES | No | Maximum output size budget per tool call (4096–65536). | 16384 |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| everything_searchA | Find file/folder paths and indexed metadata across drives or within root. Use workspace search or rg for file contents. Submit 1–8 requests; recursive:false browses; count:0 counts; add kind:"file", fields:["size"] to sum matched bytes. |
| everything_statusB | Check connection status, selected instance, version, and index readiness. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| everything-syntax | Query syntax and result semantics |
TDQS
Scored across 2 tools
The two tools have clearly distinct purposes: one performs file/folder searches, while the other reports server connection and index status. There is no meaningful overlap that would cause an agent to misselect between them.
Both names follow the same predictable snake_case convention with a consistent 'everything_' prefix and clear action/state nouns. The naming is easy to parse and internally consistent.
Two tools is on the thin side for a standalone MCP server, though the scope is narrow and each tool earns its place. The search tool is feature-rich, but the surface still feels borderline minimal.
The core domain operations are covered: searching indexed files/folders and checking connection/index readiness. Minor gaps exist, such as no explicit tool for listing or switching indexed instances or drives, but agents can likely work around them.