Alpaca Trading API integration for Model Context Protocol (MCP)
Nothing to run from here
Frontrun is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
83/100
trust score
20
downloads a day
local
runs on your machine
1k
downloads in 30d
What it does
Frontrun MCP Server - VC follow signal intelligence, company research, and deal discovery for AI agents. 35 tools.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user frontrun-mcp '--' npx -y frontrun-mcp-server
# 2 — ask your agent for something these tools do
# frontrun_status, frontrun_list_tracked, frontrun_track and 33 more
Frontrun costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
JOAll 1 server
jongall451 server
1 category
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Frontrun as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need Node.js — the current LTS (24) is the safe choice; npx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user frontrun-mcp '--' npx -y frontrun-mcp-serverReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take FRONTRUN_API_KEY (Optional — the server runs OAuth device-flow setup if unset. API + MCP access is included with the Pro plan ($99/mo) at https://www.frontrun.vc.) if you want to set it.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
36 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
Get account status: credit balance, tracked account count, usage stats, and pricing.
No parameter schema on file.
List all accounts currently being monitored for follow activity.
No parameter schema on file.
Start monitoring a Twitter/X account for follow activity. 4 credits/account.
No parameter schema on file.
Stop monitoring a Twitter/X account.
No parameter schema on file.
Preview an account before tracking. Returns profile summary, signal potential score (0-1), sector hints, and a tracking recommendation. Use this to evaluate whether an account is worth monitoring. 4 credits.
No parameter schema on file.
Detect new follows across tracked accounts. Returns temporal diffs — who each tracked account recently followed and when. 16 credits.
No parameter schema on file.
Get the current follow list for a tracked account. Shows everyone they currently follow based on stored data. 4 credits.
No parameter schema on file.
New follows with full enrichment: AI classification + custom rules + custom tags + filtering. The most powerful signal endpoint. Use sector/keyword/entity_type filters to query like
No parameter schema on file.
Detect convergence: entities followed by multiple tracked accounts independently. The highest-signal endpoint — when 3+ VCs independently follow the same account, it strongly suggests pre-funding interest. 60 credits.
No parameter schema on file.
Entities ranked by follow velocity — how many tracked accounts recently followed them. Use this for daily deal flow. 24 credits (+16 credits per item if classify=true).
No parameter schema on file.
Search discovered entities by sector, keyword, or entity type across your tracked universe. 4 credits.
No parameter schema on file.
Semantic thesis search over your database (companies surfaced by the investors you track). Describe an investment thesis in plain language (e.g.
No parameter schema on file.
Run AI classification on specific entities. Returns sector, entity type, confidence. 16 credits/entity.
No parameter schema on file.
Create a custom classification rule. Rules auto-tag entities matching your conditions in enriched follows and discover results. Free.
No parameter schema on file.
List your custom classification rules. Free.
No parameter schema on file.
Update an existing custom classification rule. Free.
No parameter schema on file.
Delete a custom classification rule. Free.
No parameter schema on file.
Add custom tags, sector override, or notes to a specific entity. Free.
No parameter schema on file.
List your custom-tagged entities. Free.
No parameter schema on file.
Synthesized company overview: what they do, sector, stage, website summary, recent activity. Combines Twitter profile, website scrape, and AI classification. 60 credits.
No parameter schema on file.
Founder intelligence: identifies founders via social graph analysis and enriches with LinkedIn data. Returns name, role, background, previous companies. 100 credits.
No parameter schema on file.
Social signal analysis: buzz score, sentiment, notable mentions, and which of your tracked VCs follow this entity. 16 credits.
No parameter schema on file.
Discovered links and resources: website, GitHub, docs, Discord, Telegram. Extracted from profile and website scrape. 60 credits.
No parameter schema on file.
Funding/deal info cross-referenced with VC follow signals. Returns round details, investors, and which of your tracked VCs follow them. 60 credits.
No parameter schema on file.
VC follow pattern analysis: velocity, sector distribution, recent follows with classification. 24 credits.
No parameter schema on file.
Find VCs with similar follow patterns. Computed from temporal follow graph overlap — not raw follower lists. Use this to discover related investors. 60 credits.
No parameter schema on file.
Real-time activity feed across tracked accounts.
No parameter schema on file.
Sector breakdown of all discovered entities across your tracked accounts. Shows distribution with counts and percentages. 4 credits.
No parameter schema on file.
Personalized account recommendations based on your tracked set and custom classification rules.
No parameter schema on file.
Historical daily reports — the companies discovered in your daily email reports. Filter by date range and sector.
No parameter schema on file.
List your registered webhooks with status and last delivery time. Free.
No parameter schema on file.
Register a webhook to receive push notifications for signal events (new_follows, convergence). Deliveries are signed with your secret if provided. 40 credits setup + 8 credits per delivery.
No parameter schema on file.
Delete a registered webhook. Free.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Frontrun or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
BTrust score 83 / 100
Release 2.7.0 · scanned 14 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score94
Client score83
Findings2 threat · 2 capability
Capabilitycritical
Coveragesource
Verificationrepo
Surface digest33dcee705f500e6b222a463dc8e445a18b90880e34adf083f3d39d03892f69dd
Score vectorthreat 94 → client 83
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | critical | capability blast radius (critical) — client exposure if the model is manipulated | −10 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (36 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. critical is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| trending_teaser | no tags | |
| send_feedback | no tags | |
| frontrun_status | no tags | |
| frontrun_list_tracked | no tags | |
| frontrun_track | no tags | |
| frontrun_untrack | no tags | |
| frontrun_preview | no tags | |
| frontrun_new_follows | no tags | |
| frontrun_snapshot | no tags | |
| frontrun_enriched_follows | no tags | |
| frontrun_convergence | no tags | |
| frontrun_trending | no tags | |
| frontrun_search | no tags | |
| frontrun_thesis_search | no tags | |
| frontrun_classify | no tags | |
| frontrun_create_rule | no tags | |
| frontrun_list_rules | no tags | |
| frontrun_update_rule | no tags | |
| frontrun_delete_rule | no tags | |
| frontrun_tag | no tags | |
| frontrun_list_tags | no tags | |
| frontrun_company | no tags | |
| frontrun_company_founders | no tags | |
| frontrun_founders_batch | no tags | |
| frontrun_company_signals | no tags | |
| frontrun_company_resources | untrusted-input | untrusted-input: keyword "scrape" |
| frontrun_company_funding | no tags | |
| frontrun_vc_activity | no tags | |
| frontrun_vc_similar | no tags | |
| frontrun_feed | no tags | |
| frontrun_sectors | no tags | |
| frontrun_discover | no tags | |
| frontrun_reports | no tags | |
| frontrun_list_webhooks | no tags | |
| frontrun_create_webhook | external-sink | external-sink: keyword "webhook" |
| frontrun_delete_webhook | external-sink | external-sink: keyword "webhook" |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
flow-1
Untrusted input can drive an external action even though no sensitive source is exposed.
Supply chain and provenance
Integrityfirst-seen
Surface digest33dcee705f500e6b
Scanned2026-10-14
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 2.7.0. Pin a release below and the command asks for exactly that one.
2.7.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Frontrun can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.