// SCAN REPORT

VibeServe

126 tools. 52 can modify or destroy data without limits.

4 destructive tools with no built-in limits. Policy required.

Last updated: 30 Jun 2026

52 can modify or destroy data

74 read-only

126 tools total

Community server · catalogue entry verified 30/06/2026

How to control VibeServe ↓

TOOL MAP

What VibeServe exposes to your agents

Read (74) Write / Execute (48) Destructive / Financial (4)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous VibeServe tools

Financial · Critical coinbase_create_charge This tool moves money or commits financial obligations by creating a charge in Coinbase Commerce, which is a payment processor. Financial · Critical stripe_create_payment This tool directly creates payment intents, which commits financial obligations and initiates money movement. Destructive · High cloudflare_purge_cache Cache purging cannot be undone; once purged, cached content is gone and must be rebuilt organically or via re-warming. Destructive · High mem0_delete The tool performs a DELETE operation on stored memories by ID, which is irreversible and cannot be undone.

52 of VibeServe's 126 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control VibeServe

PolicyLayer is an MCP gateway — it sits between your AI agents and VibeServe, and nothing reaches the server without passing your rules. These are the rules we recommend:

Block financial tools by default

{
  "coinbase_create_charge": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Requires human approval."
      }
    ]
  }
}

Financial tools should be explicitly enabled per use case, not open by default.

Deny destructive operations

{
  "cloudflare_purge_cache": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "agenda_activate_goal": {
    "limits": [
      {
        "counter": "agenda_activate_goal_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "agenda_get_active_goals": {
    "limits": [
      {
        "counter": "agenda_get_active_goals_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register VibeServe — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON VIBESERVE →

Instant setup, no code required.

FULL CATALOGUE

All 126 VibeServe tools

FINANCIAL 2 tools

Financial coinbase_create_charge Create a Coinbase Commerce charge Financial stripe_create_payment Create a Stripe payment intent

DESTRUCTIVE 2 tools

Destructive cloudflare_purge_cache Purge Cloudflare cache for the configured zone Destructive mem0_delete Delete a specific memory by ID

EXECUTE 26 tools

Execute browser_automation Control a headless browser using a Playwright-based DSL. Use for automation, scraping, or web interactions. Is Execute codegraph_build Build a knowledge graph from an indexed repo — creates call graph, import resolution, class hierarchy, and com Execute deterministic_brain Query the deterministic brain neuro-symbolic AI reasoning engine with 5 lanes: coding, business_logic, agent_b Execute google_cloud_run_query Run a Google Cloud SQL query Execute governance_kill_switch Kill switch — disable all Big-Homie agent operations Execute llm_complete Complete a prompt through Big-Homie Execute nanobot_run_skill Execute a nanobot skill by name Execute nanobot_schedule_cron Register a cron job in nanobot Execute nanobot_send Send a message through any nanobot channel Execute run_biome Run Biome linter/formatter Execute run_build Run production build Execute run_install Run package installation Execute run_npm_audit Run npm audit for dependency security Execute run_playwright Run Playwright E2E tests Execute run_semgrep Run Semgrep SAST scan on the project Execute run_tsc Run TypeScript compiler check Execute supabase_query Query a Supabase table. Execute trigger_pipeline Trigger a Nexus Alpha build pipeline for a list of repositories. Execute twilio_send_sms Send an SMS via Twilio Execute vibe_benchmark Run a benchmarking loop with ASCII graphs. Execute vibe_build_pro Full professional build: upgrade design -> architect -> code -> verify. Execute vibe_check Run all VibeCoder quality gates (type safety, lint, security, bundle, deps, structure) and return a scored bui Execute vibe_deploy Generate deployment configs for Vercel, Docker, static hosting. Execute vibe_iterate Continuous improvement loop: critique -> repair -> verify -> repeat. Execute vs_ecc_agent_shield Run ECC AgentShield security scan on provided code content. Checks for secrets, permission risks, hook injecti Execute vs_opencode_execute Execute a coding task using the OpenCode CLI agent.

WRITE 22 tools

Write agenda_activate_goal Mark a goal as active — agents will prioritize work against this goal. Write agenda_add_goal Add a single goal to the agenda with optional type, areas, due date and target metric. Write agenda_add_initiative Add an initiative linked to a goal. Write agenda_complete_goal Mark a goal as completed. Write agenda_log_entry Log a work entry (PR, refactor, test) against an agenda goal. Write agenda_set_goals Define your business objectives, priorities, and constraints for VibeServe agents to work against. Write editor_config Generate editor config files (VSCode, Zed, Cursor). Write generate_plan Generate a structured task decomposition for a given objective Write generate_ui_spec Generate a production-ready UI specification with multi-agent critique, WCAG AAA validation, and design system Write github_link_account Link a GitHub account via personal access token. Required before repo operations. Write github_link_repo Add a GitHub repo to VibeServe scope. Optionally clone it locally. Write graphify_build Build a knowledge graph from the codebase using tree-sitter AST analysis. Creates graph.json + wiki articles + Write ingest_learning Save pipeline results/learnings to the local wiki Write mem0_add Store a memory in mem0 Write memory_store Store a conversation into vector memory Write supabase_insert Insert a row into a Supabase table. Write vibe_design Generate a landing page using curated DESIGN.md templates. Write vibe_preview Generate a preview HTML page and Playwright test script. Write vibe_upgrade_design Upgrade a design template with senior-dev production patterns. Write vs_generate_artifact Generate a structured advisory artifact (not executable). Write vs_memory_store Store workspace-scoped memory for Mutly workflows. Write write_file Write content to a file in the workspace

READ 74 tools

Read agenda_get_active_goals Return all active agenda goals with full metadata. Read agenda_get_impact Get 7-day impact summary: suggestions applied per goal. Read agenda_get_status Get current agenda: goals, progress per goal, recent entries. Read analyze_repo_synergy Use Gemini AI to analyze synergies and integration opportunities across a list of repos. Read binance_get_price Get current price from Binance Read check_node_env Verify node.js environment Read codegraph_context Get 360-degree view of a symbol — all incoming/outgoing calls, inheritance, imports, and cluster membership. Read codegraph_impact Blast radius analysis — what depends on this symbol? Groups results by depth (WILL BREAK, LIKELY AFFECTED, MIG Read codegraph_query Search the knowledge graph for symbols — returns callers, callees, file locations, and export status. Replaces Read codegraph_stats Get knowledge graph statistics — node count, edge count, clusters, edge type breakdown. Read cross_repo_suggest Find reusable components/symbols from other repos that could help the current repo. Read detect_package_manager Detect which package manager to use (npm, yarn, pnpm) Read draftkings_get_contests Get DraftKings contests Read echo Echo back the given message exactly as provided. Read find_refactors Find refactor candidates: large files, duplicated symbols, dead code hints. Read find_test_gaps Find source files and symbols that have no corresponding tests. Read get_repo Get detailed information about a specific GitHub repository. Read get_time Get the current date and time in ISO 8601 format. Read github_issues List GitHub issues. Read github_list_repos List repositories for the linked GitHub account. Read github_repo Get GitHub repo info. Read github_sync_all Sync metadata for all linked repos — pulls latest data from GitHub API. Read gitnexus_analyze Index a repository with GitNexus — builds a knowledge graph of symbols, call chains, clusters, and execution f Read gitnexus_context Get a 360-degree view of a symbol — all incoming/outgoing calls, imports, processes it belongs to. Like Read gitnexus_detect_changes Pre-commit impact analysis — maps changed lines to affected processes. Use before committing to understand wha Read gitnexus_impact Analyze blast radius — what depends on this symbol? Groups results by depth (WILL BREAK, LIKELY AFFECTED, MIGH Read gitnexus_list_repos List all repositories indexed by GitNexus (across your entire machine). Read gitnexus_query Search the GitNexus knowledge graph — find symbols, processes, and definitions matching a query. Uses hybrid s Read gitnexus_status Check GitNexus index status for the current repo — is it fresh, stale, or missing? Read gitnexus_wiki Generate a codebase wiki from the GitNexus knowledge graph — architecture docs with mermaid diagrams. Read governance_check_budget Check current budget usage against configured limits Read graphify_query Query the knowledge graph instead of reading entire files. Find functions, modules, and their connections with Read graphify_summary Get a summary of the knowledge graph — top nodes, languages, connection counts. Quick overview without reading Read index_repo Index a local repository — parses source files for symbols, components, tests, and dependencies. Read list_design_systems List available design systems Read list_indexed_repos List all repos that have been indexed. Read mem0_get_all List all memories for a user Read mem0_graph_query Query the mem0 knowledge graph for entity relationships Read mem0_search Search memories by semantic similarity Read memory_search Search vector memory for past conversations Read memory_stats Get statistics on learned/stored UI specifications Read nanobot_list_skills List all available nanobot skills Read perplexity_search Search the web via Perplexity AI Read plaid_get_accounts Get linked Plaid accounts Read prizepicks_get_lines Get PrizePicks lines Read read_file Read content from a file in the workspace Read retrieve_context Retrieve context from the local wiki/knowledge base Read search_files Search for files matching a glob-like name pattern within a directory. Read search_repo Search indexed symbols across all repos, or within a specific repo. Read search_repos Search trending GitHub repos by query. Returns top 20 results with stars, forks, topics. Read sequential_think Break down complex tasks into ordered steps using Sequential Thinking MCP. Provides structured reasoning with Read shopify_get_orders List recent Shopify orders Read toon_compress Compress JSON/YAML/CSV to TOON format (30-60% token reduction). Ideal for large API responses or structured da Read toon_stats Get TOON token savings statistics — total calls, tokens saved, average reduction. Read validate_ui_spec Validate a UI specification against design system and WCAG standards Read vercel_deployments List recent Vercel deployments. Read vercel_list_deployments List Vercel deployments Read vibe_architect Transform natural language intent into a detailed architecture plan with ADR decisions. Read vibe_audit Full system audit: backend code quality, security, performance. Read vibe_code Generate production code from an architecture plan. Read vibe_compress Compress JSON to TOON format — 30-60% token reduction. Read vibe_docs Fetch documentation for a framework via Context7. Read vibe_health System health stats. Read vibe_history Get VibeCoder build history, benchmark data, improvement trends, and AI-generated optimization suggestions. Read vibe_review Multi-agent code review from three perspectives. Read vibe_score Get the latest build score without running a full check. Read vibe_test Generate comprehensive test suites from source code. Read vibe_verify Validate code/specs against WCAG, design system, and code quality. Read vs_ecc_health Check ECC integration status — skills loaded, rules available. Read vs_ecc_skills_list List available ECC skills. Optionally filter by category or harness. Read vs_memory_get Retrieve workspace-scoped memory entries for Mutly workflows. Read vs_plan_review Review an execution plan and return structured critique. Read vs_schema_validate Validate JSON data against a JSON schema. Read vs_validate_artifact Validate artifact shape and size constraints.

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about VibeServe

Can an AI agent move money through the VibeServe MCP server? +

Yes. The VibeServe server exposes 2 financial tools including coinbase_create_charge, stripe_create_payment. Without a policy, an autonomous agent can call these with no spend caps, no rate limits, and no approval flow. PolicyLayer lets you block financial tools by default, require human approval, or set per-tool rate limits — enforced on every call.

Can an AI agent delete data through the VibeServe MCP server? +

Yes. The VibeServe server exposes 2 destructive tools including cloudflare_purge_cache, mem0_delete. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through VibeServe? +

The VibeServe server has 22 write tools including agenda_activate_goal, agenda_add_goal, agenda_add_initiative. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach VibeServe.

How many tools does the VibeServe MCP server expose? +

126 tools across 5 categories: Destructive, Execute, Financial, Read, Write. 74 are read-only. 52 can modify, create, or delete data.

How do I enforce a policy on VibeServe? +

Register the VibeServe MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every VibeServe tool call.

Deterministic rules across all 126 VibeServe tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON VIBESERVE →

Instant setup, no code required.

126 VibeServe tools catalogued and risk-classified — across an index of 43,000+ MCP servers.