capx café
NPM · CAPX-CAFE · SCANNED SEP 20
Agent-native X (Twitter) posting as one MCP server; every post clears a server-side guardrail.
Available components
How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. How we score → Why this is hard to score →
Supply Chain Security98
- No malware found by supply-chain analysis.Pass
- No known CVEs affecting this package version or its production dependencies.Pass
- No install/post-install scripts declared.Pass
- 31 of 96 dependencies flagged as unhealthy. View diagnostics → Partial
Provenance & Transparency100
- Source repository is publicly reachable at the declared URL. View diagnostics → Pass
- Cryptographically verified build provenance (signed, bound to vb-tyagi/capx-cafe). View diagnostics → Pass
- Clear OSI-approved license (MIT).Pass
- Actively maintained (last published 16 days ago).Pass
- Publishes a security disclosure policy (SECURITY.md).Pass
Schema Quality & AI Usability76
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 798 tokens (~72/item across 11 items; 11 tools + 0 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management57
- Stability observed for 17 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage83
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 50% of tool parameters carry a description.Partial
Tool Safety75
- No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
- 0 of 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "delete_loop" implies "delete" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
- An AI judge read all 11 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
- Implements a supported MCP spec version (2025-11-25); the latest is 2026-07-28.Pass
How do I install the capx café MCP server?
capx café runs locally as an npm package, launched with npx -y capx-cafe. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.
npm · capx-cafe
claude mcp add vb-tyagi-capx-cafe -- npx -y capx-cafe
{
"mcpServers": {
"vb-tyagi-capx-cafe": {
"command": "npx",
"args": [
"-y",
"capx-cafe"
]
}
}
} {
"servers": {
"vb-tyagi-capx-cafe": {
"command": "npx",
"args": [
"-y",
"capx-cafe"
]
}
}
} codex mcp add vb-tyagi-capx-cafe -- npx -y capx-cafe
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"vb-tyagi-capx-cafe": {
"type": "local",
"command": [
"npx",
"-y",
"capx-cafe"
],
"enabled": true
}
}
} openclaw mcp add vb-tyagi-capx-cafe --command npx --arg -y --arg capx-cafe
mcp_servers:
vb-tyagi-capx-cafe:
command: "npx"
args: ["-y", "capx-cafe"] {
"McpServers": {
"vb-tyagi-capx-cafe": {
"Transport": "stdio",
"Command": "npx",
"Arguments": [
"-y",
"capx-cafe"
]
}
}
} assistant mcp add vb-tyagi-capx-cafe -t stdio -c npx -a -y capx-cafe
{
"mcpServers": {
"vb-tyagi-capx-cafe": {
"command": "npx",
"args": [
"-y",
"capx-cafe"
]
}
}
} Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.
- 19 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 50 to 53. That category is still filling its 30-day observation window: 15 days of observed history at the previous scan, 16 at this one. The score rises as the window fills, whether or not the server changes.
- 17 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 43 to 47. That category is still filling its 30-day observation window: 13 days of observed history at the previous scan, 14 at this one. The score rises as the window fills, whether or not the server changes.
- 15 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 37 to 40. That category is still filling its 30-day observation window: 11 days of observed history at the previous scan, 12 at this one. The score rises as the window fills, whether or not the server changes.
- 13 Sept 26 +1
No change was recorded against any check on this day. Stability & Change Management went from 30 to 33. That category is still filling its 30-day observation window: 9 days of observed history at the previous scan, 10 at this one. The score rises as the window fills, whether or not the server changes.
- 11 Sept 26 +4
- Stability: unverified → 0.27 ▲ functional
- 3 Sept 26 78
First indexed and scored.
Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.
Captured 20 Sept 2026 · Analysed npm/capx-cafe@0.1.3
Provenance Verified
A signed build attestation was found and verified, binding this exact artifact to the source repository it claims to come from.
| Result | Verified |
|---|---|
| Ecosystem | npm |
| Reason | Verified |
| Discovered via | Registry attestation endpoint |
| Source repo | vb-tyagi/capx-cafe |
| Certificate issuer | https://token.actions.githubusercontent.com |
| Certificate SAN | https://github.com/vb-tyagi/capx-cafe/.github/workflows/publish.yml@refs/heads/main |
| Rekor log index | 2697595666 |
| Predicate type | https://slsa.dev/provenance/v1 |
| Subject digest | sha512:a3f64663f91298ed34e0f495e9ed822f8ee5b472e8c2ff6980ce43fdf10adf4cf7d37fe13f0607562062e6f25636c1587284ce2d3a01258e55ddce429 |
Background: How many MCP packages publish verified provenance →
Dependencies 96 packages
| Packages resolved | 96 |
|---|---|
| Stale | 31 |
| Tree resolution | Complete |
Background: SBOMs and build attestations, explained →
The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →
audit ~56
Show the durable history of what capx has posted or attempted on your behalf (most recent first, with delivery state). A trust feature — read-only, your own handle only.
| Name | Type | Req | Description |
|---|---|---|---|
| limit | number | – | max rows (default 50) |
No output schema declared.
No examples provided.
connect_x ~69
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 }.
| Name | Type | Req | Description |
|---|---|---|---|
| clientId | string | – | – |
| confirm | boolean | – | – |
| lane | string | – | – |
No output schema declared.
No examples provided.
create_loop ~187
Schedule recurring posts. YOU (the agent) must write the posts and pass them in `posts` — 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.
| Name | Type | Req | Description |
|---|---|---|---|
| aiGenerated | boolean | – | label this loop's posts AI-assisted — the USER decides; default false |
| daysOfWeek | array | yes | 0=Sunday .. 6=Saturday, e.g. [1,3,5] |
| posts | array | yes | the posts YOU wrote; one is sent per fire, in order |
| time | string | yes | local time, HH:MM, e.g. "09:00" |
| timezone | string | – | IANA zone (defaults to this machine's), e.g. Asia/Kolkata |
No output schema declared.
No examples provided.
delete_loop ~20
Delete a loop permanently.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
No output schema declared.
No examples provided.
list_loops ~25
List your scheduled loops, their next-post queue, and whether any are paused.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
pause_loop ~35
Pause or resume a loop.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| paused | boolean | – | false to resume; defaults to true |
No output schema declared.
No examples provided.
post_now ~163
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 — it is the user's choice). Pass inReplyToId with a prior post's platformPostId to chain a native reply/thread.
| Name | Type | Req | Description |
|---|---|---|---|
| aiGenerated | boolean | – | label this post AI-assisted — the USER decides; default false |
| idempotencyKey | string | – | – |
| inReplyToId | string | – | platformPostId of the post this replies to (for threads) |
| mediaIds | array | – | media ids from upload_media to attach to this post |
| text | string | yes | – |
No output schema declared.
No examples provided.
preview ~75
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.
| Name | Type | Req | Description |
|---|---|---|---|
| aiGenerated | boolean | – | – |
| text | string | yes | – |
No output schema declared.
No examples provided.
top_up_loop ~45
Add more posts YOU wrote to a loop's queue. Resumes a loop that paused because it ran out.
| Name | Type | Req | Description |
|---|---|---|---|
| id | string | yes | – |
| posts | array | yes | – |
No output schema declared.
No examples provided.
upload_media ~100
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 — you set the AI-content label per the media skills.
| Name | Type | Req | Description |
|---|---|---|---|
| path | string | yes | local file path to the image/video, e.g. ./out/hero.png |
No output schema declared.
No examples provided.
whoami ~23
Show the connected X account and its status (via the chokepoint).
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
What is the capx café MCP server?
capx café is an MCP server listed in the public MCP registry as io.github.vb-tyagi/capx-cafe. Agent-native X (Twitter) posting as one MCP server; every post clears a server-side guardrail. This page covers its npm package (capx-cafe).
Is the capx café MCP server safe to use?
capx café scores 86 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 20 September 2026. It declares no install or post-install scripts. Its build provenance is signed and verified. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.
What tools does the capx café MCP server expose?
capx café exposes 11 tools: connect_x, whoami, post_now, preview, audit, and 6 more. Their descriptions and schemas cost roughly 798 tokens of context every time the server is loaded.
Is the capx café MCP server still maintained?
capx café is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.
What licence is the capx café MCP server under?
capx café declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.