Frontrun MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| FRONTRUN_API_KEY | Yes | Your Frontrun API key. Get one at frontrun.vc → Settings → API Keys. |
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 |
|---|---|
| frontrun_statusB | Get account status: balance, tracked account count, usage stats (last 30 days), and pricing. |
| frontrun_list_trackedB | List all accounts currently being monitored for follow activity. |
| 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+. |
| frontrun_untrackA | Stop monitoring a Twitter/X account. |
| 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. |
| frontrun_snapshotA | Get the current follow list (latest snapshot) for a tracked account. Shows everyone they currently follow. |
| 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. |
| 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. |
| frontrun_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. |
| 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. |
| 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. |
| frontrun_list_rulesB | List your custom classification rules. |
| frontrun_update_ruleB | Update an existing custom classification rule. |
| frontrun_delete_ruleC | Delete a custom classification rule. |
| frontrun_tagB | Add custom tags, sector override, or notes to a specific entity. Use this to build custom watchlists, mark competitors, or annotate companies. |
| frontrun_list_tagsA | List your custom-tagged entities. Filter by tag name or sector. |
| frontrun_classifyC | Run classification on specific entities. Returns AI classification merged with your custom rules and tags. Use this to analyze entities on demand. |
| 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. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
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.