universal-brute-workpack
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| LLM_MODEL | No | Optional model name. | provider default |
| UBW_ROOTS | No | Allowed filesystem roots, separated by ;. | * |
| UBW_CONFIG | No | Path to a custom main config JSON. | package example config |
| EXA_API_KEY | No | Optional Exa web search key. | |
| LLM_API_KEY | No | Optional model API key. | |
| UBW_PROFILE | No | Active profile. | admin |
| LLM_BASE_URL | No | Optional OpenAI-compatible base URL for Agent tasks. | |
| UBW_PROFILES | No | Path to a custom profile/deny JSON. | package example profiles |
| TAVILY_API_KEY | No | Optional Tavily web search key. | |
| UBW_MEMORY_URL | No | Optional external memory/vector service endpoint. | |
| UBW_AGENT_STAGGER_MS | No | Delay between pipeline tasks. | 0 |
| UBW_AGENT_TASK_TIMEOUT_MS | No | Agent task timeout. | 300000 |
| UBW_AGENT_MAX_PIPELINE_TASKS | No | Pipeline task cap. | 100 |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| search.webC | Search the web via configured Exa, Tavily, DuckDuckGo, or direct HTTP fallback. |
| search.fetchB | Fetch an HTTP/HTTPS URL as text. |
| fs.globC | List files matching a glob-like pattern. |
| fs.grepC | Search file contents under a root using the local worker pool for large trees. |
| fs.listC | List a directory. |
| file.readC | Read a file. |
| file.writeD | Write a file. |
| file.copyC | Copy a file or directory. |
| file.moveC | Move a file or directory. |
| code.patchB | Apply exact text replacements and run syntax check for JS-like files. |
| code.reviewC | Run a structured heuristic code review over a file or directory. |
| command.execC | Execute a local shell command. |
| validate.checkC | Run a lightweight syntax/config check. |
| validate.loadC | Load JSON or JS modules and return a structured summary. |
| validate.diffB | Return git diff for a cwd/path when git is available. |
| memory.searchB | Search memory through an external service, then local text files as fallback. |
| memory.recallC | Alias of memory.search for Agent clients that use recall wording. |
| worker.analyzeC | Analyze files in parallel for size, extension, line, TODO, and FIXME summaries. |
| worker.diffC | Parallel file or directory diff by sha256, size, and existence. |
| audit.prepareC | Prepare a host-mediated audit runDir with TaskCards, prompts, manifest, and report dropbox. |
| audit.ingest_reportC | Ingest one host-mediated worker report into an audit runDir. |
| audit.runC | Run a TaskCard/runDir/collector/EvidenceBundle audit pipeline. |
| audit.collectC | Collect an existing audit runDir into an EvidenceBundle and gate file. |
| worker.statusA | Return local workpack, worker-pool, and sidecar status. |
| agent.spawnC | Spawn one external agent through the configured sidecar adapter. |
| agent.pipelineC | Run an external multi-agent pipeline through the managed sidecar adapter. |
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/haoyun18881-beep/universal-brute-workpack'
If you have feedback or need assistance with the MCP directory API, please join our Discord server