Skills/npm/mcp-server

mcp-server@2.3.0

VERIFIED· install only

Publisher claims: "Official Speak AI MCP Server — capture meetings, search thousands of recordings, run async voice and video surveys, create clips, and automate workflows from your AI assistant." Observed in sandbox: no network, touches nothing outside the project, writes no memory.

Registry npm (MCP server)Publisher speakai · publishing for 243 daysInstalls 8,270Last detonated 14 min ago
$claude mcp add mcp-server -- npx -y @speakai/mcp-server
WatchReport an issue

Coverage

Nothing executable in the bundle ran; the trace covers the install step only.
Tested
every file read, file written and host contacted by what ran
Not tested
use of the skill by an agent

What this means for the label: Verified here covers what ran. The server's tools were not exercised with a real credential, so nothing about their behavior is asserted; the credential summary below says what to do with that.

Before you give it your token

It will ask for
no credential variables read in the code
Where it talks to
no vendor host named in the code
What we saw when it ran
no credential files read · no network
What we could not test
use of the skill by an agent

Connect it under the guard. Nothing executable in the bundle ran; the trace covers the install step only. The code names no credential variable; the guard pins the network to what the honeypot saw and logs every call.

$vet-skills run --net declared -- npx -y @speakai/mcp-server

Never paste a credential into a chat, a ticket or a report, including ours. How the guard holds it.

What changed since 2.0.0

vet-skills diff mcp-server 2.0.0 2.3.0

In the sandbox, this version reached for nothing 2.0.0 did not. Compared from the two recorded runs, not from source.

The guard can hold an update like this until someone approves it (runtime.on_change: hold). A change that only shows with a real credential, or on a path the run did not reach, is not in a trace and so not in this comparison.

Is [email protected] safe to install?

KillerSkills ran it in the KillerSkills honeypot sandbox (1 scenario; nothing executable in the bundle ran; the trace covers the install step only) on 2026-11-21 and scored it 89/100 (Verified). In what ran, nothing we could detect went wrong: no undeclared network egress, no credential reads, no persistent instruction writes. What it does with a real credential was not observed; the static findings and the publisher carry the rest of the score. Summary: no network, touches nothing outside the project, writes no memory.

Behavior trace

Honeypot run · 0 s · 1 scenarios · 0 deviations
t+CategoryObserved action
0.0sprocessno install scripts in bundle
0.0sprocessscript backend runs setup only
0.0sprocessscript backend runs setup only
0.0sprocessno install scripts to re-run

Static findings

LOW
Fake instruction boundary tagREADME.md:928 · Fake instruction boundary tag · informational: not an instruction file| `ask <prompt>` | Ask AI about media, folders, or your whole workspace |Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:67 · Collapsed <details> block carrying instructions<summary>Developer alternative: manual setup with an API key</summary> Get a key at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
LOW
Prompt injectionREADME.md:121 · Prompt injection — known jailbreak technique reference · informational: not an instruction file…ustom connector instead: **Settings → Apps & Connectors → Advanced**, turn on **Developer Mode**, click **Create**, paste `https://api.speakai.co/v1/mcp` and choose **OAuth**…Fix: Keep SKILL.md to visible, descriptive text. Remove comments and encoded text that address the agent.
AST01
LOW
Authorization escalation languageREADME.md:121 · Authorization escalation language · informational: not an instruction file…ustom connector instead: **Settings → Apps & Connectors → Advanced**, turn on **Developer Mode**, click **Create**, paste `https://api.speakai.co/v1/mcp` and choose **OAuth**…Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:81 · Collapsed <details> block carrying instructions<summary>Developer alternative: manual setup with an API key</summary> Get a key at [app.speakai.co/developers/apikeys](https://app.speakai.co/developers/apikeyFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:205 · Collapsed <details> block carrying instructions<summary>Alternative: local setup with an API key</summary> Use the manual stdio setup in the Developer reference at the bottom of this README.Fix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:149 · Collapsed <details> block carrying instructions<summary>Alternative: send an API key instead of signing in</summary> ```sh claude mcp add --transport http speakai https://api.speakai.co/v1/mcp \ --header "AuFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:115 · Collapsed <details> block carrying instructions<summary>Trouble connecting?</summary> - **Authorization tab doesn't show a "you're connected" page**: if you land on the plain Speak AI dashboard with no confiFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01
HIGH
Collapsed <details> block carrying instructionsREADME.md:175 · Collapsed <details> block carrying instructions<summary>Alternative: send an API key instead of signing in</summary> ```sh export SPEAKAI_KEY="your-api-key" codex mcp add speakai --url https://api.speakai.coFix: Remove the text that addresses the agent rather than the reader; describe behavior, do not instruct.
AST01

Cost to the agent

Instructions loaded
≈81 tok
1 file · 4 in bundle

Tokens estimated at four characters each. Skills load their instruction text when triggered; the figure is what that costs.

Known vulnerabilities

Not checked against OSV yet; the weekly check has not reached this version.