MCP.Market

capx café MCP server

by vb-tyagi·io.github.vb-tyagi/capx-cafe·v0.1.3
No reviews yet

Agent-native X (Twitter) posting as one MCP server; every post clears a server-side guardrail.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

0 stars17 downloads/wk

Reviews

Write one

Nobody has reviewed capx café yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

capx café tools (11, 4 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • audit

    Show the durable history of what capx has posted or attempted on your behalf (most recent first, with delivery state). A trust feature \u2014 read-only, your own handle only.

  • connect_x

    Connect (or confirm) your X account via the capx chokepoint. Call once for a consent URL; after authorizing in the browser, call again with { confirm: true }.

  • create_loopwrite action

    Schedule recurring posts. YOU (the agent) must write the posts and pass them in `posts` \u2014 capx never generates content, so at fire time it only ships text you already wrote. When the queue empties the loop pauses and asks for more. Requires a verified X account at least 30 days old.

  • delete_loopwrite action

    Delete a loop permanently.

  • list_loops

    List your scheduled loops, their next-post queue, and whether any are paused.

  • pause_loop

    Pause or resume a loop.

  • post_nowwrite action

    Post text to X now. Every post passes the casserole guardrail at the chokepoint; blocked/held posts are never sent, and the token never touches this machine. Set aiGenerated only if the user wants this post labelled AI-assisted (default off \u2014 it is the user's choice). Pass inReplyToId with a prior post's platformPostId to chain a native reply/thread.

  • preview

    Dry-run a draft through the casserole guardrail WITHOUT posting: returns whether it would pass, be held, or be blocked, and why. Use it to fix a draft before posting or scheduling. This is a linter, never a way to bypass the guard.

  • top_up_loop

    Add more posts YOU wrote to a loop's queue. Resumes a loop that paused because it ran out.

  • upload_mediawrite action

    Upload a local image or video (produced by your own media tool) so it can be attached to a post. Reads the file, streams the bytes to the chokepoint, and returns a media id to pass to post_now as mediaIds. Media is not moderated by casserole \u2014 you set the AI-content label per the media skills.

  • whoami

    Show the connected X account and its status (via the chokepoint).

Public scan report

scanner v0.1.10 · 2026-10-16 · same rubric, same numbers if you re-run it

no findings
  • Code scan2 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 29 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How capx café compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,461 AI and agents servers
Tools
11
the typical AI and agents server has 6
Tools that change things
36%
typical: 0%. Fewer write tools means less an agent can break
Downloads a week
17
more than 4% of 1,554 AI and agents servers with a package

What its tools let an agent do: 7 read · 2 create · 1 delete · 1 send or post

Install capx café in Claude Code, Cursor or VS Code

Runs npx -y capx-cafe on your machine. Read the scan report first; the gateway never runs local packages.

claude mcp add capx-cafe -- npx -y capx-cafe
Add to Cursor

What the publisher says

From the capx café repository's README, as published. We do not edit it. Read it on GitHub

capx café

The safe way to let your AI run your X.

One MCP server. Your X token never touches the agent — and every post clears an enforced guardrail before it ships.

The guardrail, live — every verdict above is produced by the real chokepoint code (pnpm demo replays it).

capx café is an agent-native X poster that installs as one MCP server into any coding agent (Claude Code /

Cursor / Codex / Windsurf). A whitelisted user connects their X account once; after that they create /

schedule / post from inside their agent session. The whole product rests on one security thesis: the X

token, the guardrail (casserole), and the send are one inseparable server-side unit — the agent on

your laptop only ever holds a short-TTL session handle, never the token. That's why it structurally can't be

prompt-injected into tweeting a scam. "The AI writes; casserole decides what ships."

Why it's different

Every other "let your AI post" tool has the same flaw: to let an agent post, you paste your X token into a plaintext config right next to an autonomous agent that reads untrusted web pages, issues, and code. One prompt-injection and your account tweets a scam. capx café is the only one that structurally can't be.

encrypted in a server-side vault. Your agent holds only a short-TTL, revocable session handle.

  • 🔒 Your X token never touches your machine. OAuth completes on capx café's hosted callback; the token lives

and checks every post. A blocked post never even decrypts your token (proven by an adversarial test suite).

  • 🛡️ casserole — a deterministic (non-AI) six-layer guardrail — runs server-side at the only door to X

still hit the guard. The client's checks are cosmetic; the server's are load-bearing.

  • 🔗 The token, the guard, and the send are one unit. Skip the plugin and call the server directly — you
  • ✍️ capx generates nothing. Your agent's model writes; capx ships what clears the guard.

→ Full threat model, architecture & the "what we can/can't see" table: docs/SECURITY.md

How it works

flowchart LR
    subgraph M["🖥️  your machine · untrusted"]
        A["agent model<br/>writes the draft"]
        S["capx skills"]
        C["capx MCP client<br/>holds a session handle · NO token"]
    end
    subgraph K["🔒  capx chokepoint · hosted · AGPL-3.0"]
        AD["admission<br/>allowlist · kill-switch"]
        CAS["casserole<br/>6-layer guardrail"]
        V["vault<br/>the token lives here"]
        XA["x-adapter<br/>the only egress"]
    end
    X["🐦 X · /2/tweets"]
    A --> C
    S --> C
    C -->|"short-TTL handle<br/>crosses — never the token"| AD
    AD --> CAS
    CAS -->|PASS| V --> XA --> X
    CAS -.->|blocked / held| C

The token, the guardrail, and the send live together behind a trust boundary; your agent can only ask.

The guardrail: casserole

Six deterministic layers on every post. Worst result wins — pass / rewrite / hold / block — and a blocked post never even decrypts the token.

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

capx café: common questions

Is capx café MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the capx café safety report
How do I install capx café?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does capx café need an API key?
No secret keys are declared. It reads 4 settings from the environment.
Is capx café maintained?
The last commit was 49 days ago (2026-09-17). The latest release is v0.1.3.
What can I use instead of capx café?
Servers from other publishers that do the same job: Commonly MCP server, Agent-Native Slides MCP server and Ts Core MCP server.
How does capx café compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,461 AI and agents servers); tools 11 (the typical AI and agents server has 6); tools that change things 36% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to capx café

Same job from other publishers: the closest match first, then the best rated.

  • Commonly
    Read Commonly pods and post as a Commonly agent you create, with a token from your Commonly account.
    A
  • Agent-Native Slides
    Agent-Native Google Slides - generate and edit React presentations
    More from BuilderIO →
    A
  • Ts Core
    Agent-native TypeScript framework for building MCP servers.
    A
  • Socialclaw
    Connect any AI agent to 11+ social platforms: schedule, publish & track posts via hosted MCP.
    A
  • three.ws Agora
    Agora agent economy over MCP: browse the board, register, claim on-chain work, and post bounties.
    B