VegaMCP
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SENTRY_ORG | No | Sentry organization slug | |
| SEARXNG_URL | No | Self-hosted search fallback | |
| GITHUB_TOKEN | No | GitHub API (60→5000 req/hr) | |
| KIMI_API_KEY | No | Kimi K2.5 for coding | |
| SENTRY_PROJECT | No | Sentry project name | |
| TAVILY_API_KEY | No | AI-powered web search | |
| DEEPSEEK_API_KEY | No | Direct DeepSeek API (R1 + Chat) | |
| SENTRY_AUTH_TOKEN | No | Error tracking | |
| OPENROUTER_API_KEY | No | Supports ALL models via OpenRouter | |
| VEGAMCP_TOOL_PROFILE | No | full | minimal | research | coding | ops | full |
| TOKEN_DAILY_BUDGET_USD | No | Daily budget in USD | 5.00 |
| TOKEN_HOURLY_BUDGET_USD | No | Hourly budget in USD | 1.00 |
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 | {} |
| logging | {} |
| prompts | {} |
| resources | {} |
| completions | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| omni_assistantC | Core AI intelligence: reasoning, budget, auto-update, prompts, web search (speed/balanced/quality modes + domain filter), code analysis, docs, sequential thinking, expert toolkits, knowledge engine, memory graph, semantic memory (vector search), context7 library docs. |
| omni_swarmC | Agent orchestration: swarm ops, agent intel/ops, A2A protocol, agent graphs, agentic sampling, multimodal embeddings, session manager, MCP relay. |
| omni_automationC | Action & control: browser, workflow, filesystem, shell, git, MCP tasks, API requests, sandbox, watchers, webhooks, schedule, notify, the_claw, claw_command_center, vps_control, image_generation. |
| omni_systemsD | Infrastructure: database, postgres_client, health check, analytics, skills, seed data, sentry, OAuth, gateway, tool search, MCP apps, vault, dynamic indexing. |
| omni_researchD | Research & Science: graph RAG, agentic RAG, self evolution, hypothesis gen, quality gate, synthesis engine, LLM router, memory bridge, tool discovery, sentinel, LLM output evaluation. |
| omni_testingC | QA & Security: mobile, web, API, DB, server, desktop, accessibility, security, visual, advanced testing, security scanner, stress test, zero trust. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| investigate_error | Investigate a production error by chaining: Sentry lookup → source correlation → fix. |
| architecture_review | Review the project architecture by querying the memory graph and analyzing patterns. |
| research_pipeline | Run a multi-agent research pipeline: research → analyze → review → summarize. |
| swarm_status_report | Generate a comprehensive status report of the agent swarm, including agent health, task metrics, and system performance. |
| code_review_pipeline | Execute a full code review pipeline: analyze code → critique → suggest improvements → summarize. |
| content_pipeline | Generate polished content: research → draft → critique → revise → publish. |
| project_planning | Create a project plan: decompose tasks → estimate → identify dependencies → generate roadmap. |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| All Memory Entities | Browse all entities in the persistent knowledge graph with observation counts. |
| Project Architecture Entities | Entities in the project-arch domain. |
| Coding Style Entities | Entities in the coding-style domain. |
| Bug History Entities | Entities in the bug-history domain. |
| General Entities | Entities in the general domain. |
| All Memory Relations | Browse all relationships between entities in the knowledge graph. |
| Swarm Status | Live status of all agents, active tasks, and coordinators. |
| Active Tasks | Currently running and queued swarm tasks. |
| Metrics Dashboard | Aggregated performance metrics across all agents. |
| Event Triggers | All registered event triggers and their fire history. |
TDQS
Scored across 6 tools
Tools have extremely broad and overlapping descriptions (e.g., omni_assistant and omni_research both cover RAG and knowledge; omni_automation and omni_swarm both involve orchestration). An agent would struggle to distinguish which tool to use for a given task.
All tools follow a consistent 'omni_<noun>' pattern. However, the nouns (assistant, automation, research, swarm, systems, testing) are vague and do not clearly indicate the tool's unique scope.
With only 6 tools covering an enormous range of capabilities (from AI assistants to infrastructure to testing), the set is under-scoped. Each tool effectively contains multiple distinct functionalities that should probably be separate tools.
The tool set covers many domains (AI, automation, research, orchestration, infrastructure, testing), but there are noticeable gaps such as dedicated monitoring, deep analytics, or security scanning beyond basic mentions. The overlap also indicates incomplete separation of concerns.