high-performance-mcp-server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | Default HTTP port override. Strict integer 1-65535, used with --transport=http. | 3000 |
| MCP_PROFILE | No | Default tool profile override. One of: safe, workspace, workspace_write, network, diagnostics, benchmark, admin, all. | safe |
| MCP_ROOTS_JSON | No | JSON array of workspace roots, e.g. ["/home/user/project", "/home/user/docs"]. | |
| MCP_CACHE_TTL_MS | No | LRU compute cache entry Time-to-Live in milliseconds. 5 minutes. | 300000 |
| MCP_WORKER_COUNT | No | Number of worker threads spawned in the pool. 1 to 16. | 4 |
| MCP_CACHE_MAX_ENTRIES | No | Maximum entries in the LRU compute cache. 1 to 10000. | 256 |
| MCP_NETWORK_HTTPS_ONLY | No | Enforce HTTPS-only mode for all network requests. Accepts true/1/false/0. | false |
| MCP_NETWORK_CACHE_TTL_MS | No | Max cache retention TTL override in ms. 1000 to 3600000. | 300000 |
| MCP_NETWORK_CACHE_ENABLED | No | Enable conditional in-memory response cache. Accepts true/1/false/0. | false |
| MCP_NETWORK_MAX_TIMEOUT_MS | No | Operator request timeout cap in ms override. 1000 to 30000. | 30000 |
| MCP_NETWORK_DENY_HOSTS_JSON | No | JSON array of denied host patterns, e.g. ["ads.example.com"]. | |
| MCP_NETWORK_ALLOW_HOSTS_JSON | No | JSON array of allowed public host patterns, e.g. ["example.com","*.githubusercontent.com"]. | |
| MCP_NETWORK_CACHE_MAX_ENTRIES | No | Max cache entries override. 1 to 512. | 128 |
| MCP_WORKSPACE_MAX_WRITE_BYTES | No | Operator hard cap for text write/edit size in bytes. 1 to 5242880. | 1048576 |
| MCP_NETWORK_MAX_RESPONSE_BYTES | No | Operator response byte cap override. 1 to 5242880. | 5242880 |
| MCP_NETWORK_CACHE_MAX_SIZE_BYTES | No | Logical max cache payload size override in bytes. 1024 to 67108864. | 16777216 |
| MCP_WORKSPACE_MAX_RESOURCE_BYTES | No | Operator hard cap for resource read size in bytes. 1 to 5242880. | 1048576 |
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
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| echoA | Echoes back the provided message |
| pingA | Checks whether the MCP server is responsive |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/AnIayana/high-performance-mcp-server'
If you have feedback or need assistance with the MCP directory API, please join our Discord server