Frontrun MCP Server
The Frontrun MCP Server gives AI agents real-time access to the Frontrun API for monitoring X (Twitter) accounts — primarily venture capitalists — to detect investment signals, follow trends, and analyze market activity.
Account Management
Check account status, balance, usage stats, and pricing (
frontrun_status)Start (
frontrun_track) or stop (frontrun_untrack) monitoring X accountsList all currently monitored accounts (
frontrun_list_tracked)
Follow Tracking & Analysis
Detect new follows across all tracked accounts within a configurable time window (
frontrun_new_follows)Get the full current follow list for any tracked account (
frontrun_snapshot)Analyze a specific account's activity profile including follow velocity and sector distribution (
frontrun_account_activity)
Signal Detection
Identify convergence signals — entities independently followed by multiple tracked accounts, indicating strong pre-funding interest (
frontrun_convergence)Get trending entities ranked by how many tracked accounts recently followed them (
frontrun_trending)
Search & Classification
Search discovered entities by sector, keyword, or type (startup, VC fund, accelerator, etc.) (
frontrun_search)Run AI classification on specific entities for sector and type labels (
frontrun_classify)Retrieve new follows with full AI + custom rule enrichment merged (
frontrun_enriched_follows)
Custom Rules & Tagging
Create, list, update, and delete custom classification rules that auto-tag entities based on bio keywords, sector, or username patterns (
frontrun_create_rule,frontrun_list_rules,frontrun_update_rule,frontrun_delete_rule)Add custom tags, sector overrides, or notes to specific entities for watchlists or competitor tracking (
frontrun_tag)List all custom-tagged entities, filterable by tag or sector (
frontrun_list_tags)
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Frontrun MCP Server Show me trending companies across my monitored VCs this week"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Frontrun MCP Server
VC follow intelligence for AI agents. Track what top investors follow on X — detect new follows, convergence signals, and trending companies before they're announced.
33 tools. Version 2.5.2.
Setup (1 minute)
Option A: OAuth login (recommended)
No API key needed. Log in with your frontrun.vc account:
# Step 1: Log in — opens browser, saves credentials locally
npx frontrun-mcp-server --login
# Step 2: Auto-configure your client
npx frontrun-mcp-server --setup # Claude Desktop
npx frontrun-mcp-server --setup-code # Claude Code (uses `claude mcp add`)Credentials are saved to ~/.frontrun/credentials.json. Other commands:
npx frontrun-mcp-server --status # Check auth status
npx frontrun-mcp-server --logout # Clear saved credentialsOption B: Hosted endpoint (no install)
The server is also hosted at https://www.frontrun.vc/mcp (streamable HTTP). Point any
remote-capable MCP client at it with your API key:
claude mcp add --transport http frontrun https://www.frontrun.vc/mcp --header "Authorization: Bearer sig_your_key_here"Option C: Manual API key
If you prefer to use an API key directly, go to frontrun.vc → Settings > API Keys and generate a key (starts with sig_).
claude mcp add frontrun -e FRONTRUN_API_KEY=sig_your_key_here --scope user -- npx frontrun-mcp-serverOr add to .mcp.json in any project:
{
"mcpServers": {
"frontrun": {
"command": "npx",
"args": ["frontrun-mcp-server"],
"env": {
"FRONTRUN_API_KEY": "sig_your_key_here"
}
}
}
}Add to your config file:
macOS:
~/Library/Application Support/Claude/claude_desktop_config.jsonWindows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"frontrun": {
"command": "npx",
"args": ["frontrun-mcp-server"],
"env": {
"FRONTRUN_API_KEY": "sig_your_key_here"
}
}
}
}Add to .cursor/mcp.json in your project:
{
"mcpServers": {
"frontrun": {
"command": "npx",
"args": ["frontrun-mcp-server"],
"env": {
"FRONTRUN_API_KEY": "sig_your_key_here"
}
}
}
}FRONTRUN_API_KEY=sig_your_key_here npx frontrun-mcp-serverStart asking questions
Open your AI tool and try:
"What's trending in my tracked accounts this week?"
Related MCP server: Spectre
What can I ask?
Here are real prompts that work out of the box. Just type them into Claude Code, Claude Desktop, or Cursor.
Daily deal flow
"What are the trending companies this week?"
"Show me what my tracked VCs followed in the last 48 hours"
"Any convergence signals? Who are multiple VCs following independently?"
Deep research
"Tell me everything about @hitdotone — who founded it, what they're building, and who's backing them"
"Who are the founders of @someproject and what's their background?"
"What funding has @tempofinance raised?"
Discovery
"Find me early-stage DeFi companies that my tracked VCs are following but I'm not tracking yet"
"What sectors are getting the most attention from VCs right now?"
"Search for stablecoin startups in the follow graph"
Portfolio monitoring
"Track @a16zcrypto and @paradigm"
"Show me a16zcrypto's recent follow activity and what sectors they're focused on"
"Find VCs with similar follow patterns to @multicoin"
Custom intelligence
"Create a rule to flag any stablecoin neobank companies"
"Tag @hitdotone as a portfolio candidate"
"Show me all entities matching my stablecoin rule from the last 7 days"
How it works
Frontrun monitors the X (Twitter) follow graphs of VCs and investors you choose to track. When a VC follows a new account, Frontrun detects it, classifies the entity (startup, protocol, founder, etc.), and makes it queryable through AI.
The signal: VCs typically follow companies 2-8 weeks before a funding announcement. Convergence — multiple VCs independently following the same account — is the strongest signal.
Receipts: @techdollarhq flagged at 13 followers, $3M pre-seed announced 123 days later · @orthogonal_sh flagged 184 days before its $4.3M round led by Pantera · @rialto_xyz flagged at 18 followers, 26 days before its Robinhood partner announcement.
What you're paying for: Every response is computed intelligence, not raw data. Sectors are classified by AI, convergence is detected algorithmically, and company profiles are synthesized from multiple sources.
Pricing
API + MCP access is included with the Pro plan ($99/mo) — it comes with 10,000 credits every month, and you can add more (or turn on auto-refill) at frontrun.vc/api/billing. Each query costs credits:
What you're doing | Credits |
Check your balance, list tracked accounts, manage rules/tags | Free |
Preview an account, search, view sectors, pull a report | 4 |
New follows, enriched follows, feed, company signals | 16 |
Trending scan, VC activity | 24 |
Thesis search, webhook setup (then 8/delivery) | 40 |
Company deep-dive: overview, funding, convergence, resources, discover, similar VCs | 60 |
Founder intelligence | 100 |
A typical daily check-in (feed + convergence + a few company deep-dives) runs ~300 credits — an included month covers it more than 30x over. Agent-scale usage is what auto-refill is for.
All available tools
The agent has access to these tools automatically. You don't need to call them by name — just ask your question and the agent picks the right tool.
Tracking
Tool | What it does |
| Your balance, tracked count, usage stats |
| All accounts you're monitoring |
| Start monitoring an X account |
| Stop monitoring an account |
| Preview an account before tracking — signal score, sector hints, recommendation |
Signals
Tool | What it does |
| New follows detected across your tracked accounts |
| Current follow list for a specific tracked account |
| New follows + AI classification + custom rules applied |
| Multiple tracked accounts following the same entity |
| Entities ranked by follow velocity |
| Search discovered entities by sector, keyword, type |
| Semantic search — describe a thesis in plain language, get matching companies |
| Real-time activity feed across all tracked accounts |
| Sector breakdown of discovered entities |
| Personalized recommendations — "accounts your VCs follow that you're not tracking" |
| Generated intelligence reports for your tracked accounts |
Company intelligence
Tool | What it does |
| Company overview — what they do, sector, stage |
| Founder profiles, backgrounds, previous companies |
| Social buzz, sentiment, notable engagements |
| Website, GitHub, docs, community links |
| Funding rounds, investors, amounts |
VC intelligence
Tool | What it does |
| VC follow patterns — velocity, sector focus, recent follows |
| Find VCs with overlapping follow patterns |
Classification
Tool | What it does |
| Run AI classification on specific entities |
| Create a custom classification rule |
| List your rules |
| Update a rule |
| Delete a rule |
| Tag an entity with custom labels |
| List your tagged entities |
Webhooks
Tool | What it does |
| List your registered webhooks |
| Register a webhook for new_follows / convergence events |
| Delete a webhook |
REST API
Prefer HTTP? Every tool maps to a REST endpoint. Base URL: https://frontrun.vc/v1
# Set your key
export FR_KEY="sig_your_key_here"
# Check your account
curl -sL -H "X-API-Key: $FR_KEY" "https://frontrun.vc/v1/status"
# What's trending?
curl -sL -H "X-API-Key: $FR_KEY" "https://frontrun.vc/v1/trending?since=168h"
# Convergence signals
curl -sL -H "X-API-Key: $FR_KEY" "https://frontrun.vc/v1/convergence?since=168h"Full REST docs: frontrun.vc/docs/api
Support
License
MIT
Available Tools
18 toolsfrontrun_account_activityA
Get activity profile for a tracked account: follow velocity, sector distribution, snapshot coverage, and recent follows with classification. Use this to analyze a specific VC's recent behavior.
Inputs: username (required), since.
frontrun_classifyC
Run classification on specific entities. Returns AI classification merged with your custom rules and tags. Use this to analyze entities on demand.
Inputs: usernames, twitter_user_ids.
frontrun_convergenceA
Detect convergence: entities followed by multiple tracked accounts independently within a time window. Higher threshold = stronger signal. This is the highest-signal endpoint — when 3+ VCs independently follow the same account, it strongly suggests pre-funding interest.
Inputs: threshold, since.
frontrun_create_ruleA
Create a custom classification rule. Rules auto-tag entities matching conditions (bio keywords, sector, username pattern). Use this to build custom watchlists, sector taxonomies, or competitor tracking.
Inputs: name (required), conditions (required), actions (required).
frontrun_delete_ruleC
Delete a custom classification rule.
Inputs: id (required).
frontrun_enriched_followsB
Get new follows with full enrichment: AI classification + your custom rules + your custom tags, all merged. This is the most powerful endpoint for custom workflows.
Inputs: since, username.
frontrun_list_rulesB
List your custom classification rules.
Inputs: no named parameters.
frontrun_list_tagsA
List your custom-tagged entities. Filter by tag name or sector.
Inputs: tag, sector.
frontrun_list_trackedB
List all accounts currently being monitored for follow activity.
Inputs: no named parameters.
frontrun_new_followsA
Detect new follows across tracked accounts by diffing consecutive snapshots. Returns who each tracked account recently followed. Use this to see what VCs/accounts noticed recently.
Inputs: since, username, classify.
frontrun_searchB
Search discovered entities by sector, keyword, or entity type. Searches across all accounts followed by your tracked set. Use this to find companies in a specific space.
Inputs: sector, keyword, entity_type, limit.
frontrun_snapshotA
Get the current follow list (latest snapshot) for a tracked account. Shows everyone they currently follow.
Inputs: username (required).
frontrun_statusB
Get account status: balance, tracked account count, usage stats (last 30 days), and pricing.
Inputs: no named parameters.
frontrun_tagB
Add custom tags, sector override, or notes to a specific entity. Use this to build custom watchlists, mark competitors, or annotate companies.
Inputs: twitter_user_id, username, tags, custom_sector, +2 more.
frontrun_trackB
Start monitoring a Twitter/X account. When this account follows someone new, it will appear in new follows and convergence data. Costs $0.10 for standalone users, free for SaaS Pro+.
Inputs: username (required).
frontrun_trendingA
Get entities ranked by number of tracked accounts that recently followed them. Sorted by follower_count descending. Use this for daily deal flow — see what VCs are paying attention to.
Inputs: since, limit, classify.
frontrun_untrackA
Stop monitoring a Twitter/X account.
Inputs: username (required).
frontrun_update_ruleB
Update an existing custom classification rule.
Inputs: id (required), name, conditions, actions, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 18 tools
Every tool has a clearly distinct purpose with no ambiguity. For example, frontrun_account_activity analyzes a specific account's behavior, frontrun_convergence detects multi-account follow patterns, and frontrun_new_follows shows recent follows from tracked accounts. The descriptions clearly differentiate each tool's function, making misselection unlikely.
All tool names follow a consistent verb_noun pattern with the 'frontrun_' prefix, such as frontrun_create_rule, frontrun_list_tags, and frontrun_track. This uniformity makes the toolset predictable and easy to navigate, with no deviations in naming style.
With 18 tools, the count is slightly high but reasonable for the server's purpose of monitoring and analyzing social media follow activity. It covers tracking, classification, rule management, and data retrieval comprehensively, though it might be borderline heavy for some use cases.
The toolset provides complete CRUD/lifecycle coverage for the domain, including tracking (track/untrack), rule management (create/update/delete/list), data retrieval (account_activity, snapshot, new_follows), and analysis (convergence, trending, search). There are no obvious gaps that would hinder agent workflows.
Maintenance
Related MCP Connectors
Funding rounds, AI startup and investor search, email discovery, agent-readiness. No API key.
Evidence-backed capital-change intelligence and sourced financial data for AI agents
B2B lead finding, company enrichment, email discovery and funding tracking as 10 agent tools.
Private company data, entity-resolved news, targeted lists, and alternative signals for AI agents.
Related MCP Servers
AlicenseAqualityDmaintenanceProvides Cursor AI agents with direct access to stock breakout signals, including trending tickers, AI-generated reports, portfolio tracking, and watchlist management, all aggregated and scored from multiple sources.2223 npmMIT- AlicenseCqualityCmaintenanceEnables AI agents to search, read user profiles, timelines, media, follow threads, track trends, and manage accounts on X/Twitter via GraphQL, without browser automation or paid API keys.10011MIT
- AlicenseNot gradedqualityDmaintenanceProvides social intelligence tools for AI agents to analyze competitor sentiment, trends, and brand mentions from X/Twitter data.MIT
- FlicenseNot gradedqualityBmaintenanceConnects Claude or any MCP-compatible AI to a database of 960+ active VC funds for searching, fund profiles, live GP signals, and AI-powered startup-investor matching.1-