teleconference-mcp (sandraschi/teleconference-mcp) is an MCP server listed on the M8ven Trust Index. It scores 73 out of 100, grade C. It declares 44 tools. No publisher has claimed this listing.

Back to MCP Trust IndexM8ven
C
Caution
73/100

teleconference-mcp

Video conferencing with AI voice agent integration, built on Turborepo and LiveKit.

→ sandraschi/teleconference-mcp· listed on github_repo_search

Caution. Specific findings reduced this grade. They are listed on the page. Grades reflect the full trust pyramid: code, verification depth, and reputation. New projects cap at C until adoption is earned.

How we verified

⚡ Live Monitored: not connected

Verified is a snapshot. Live keeps it current, and builds your track record.

⚡ Connect GitHub → continuous verification on every pushwhy connect →

Who stands behind it

sandraschi

Source: github_repo_search

Is this your MCP?

Claim it to get a verified publisher badge, a free copy of our full audit findings, and direct contact for any high-priority issues we find. Or connect your repo for our deepest verification, Live Monitored: read-only, revoke anytime. What we access →

⚡ Connect GitHub for Live Monitored

Install from

GitHub

The grade above is for the source repository. Registries can serve a different version, so we mark the ones we were not able to read.

// key findings
🚨
Secret credentials may flow to a network call
3 flows detected: OPENAI_API_KEY, DEEPGRAM_API_KEY, META_API_KEY. We can’t prove the destination matches the brand the credential belongs to.
⚠️
Tool descriptions don’t match what handlers do
2 tools describe read intent but their handlers mutate — get_dev_stats (line 28: git_branch = subprocess.run(["git", "branch", "--show-current"], capture_output=True, text=True).std); query_system_logs (line 87: proc = subprocess.run(["powershell", "-Command", cmd], capture_output=True, text=True, check=True))
🔐
You'll be asked for 5 credentials: META_API_KEY, OPENAI_API_KEY, DEEPGRAM_API_KEY, LIVEKIT_API_KEY, LIVEKIT_API_SECRET
These are read from process.env at runtime. Make sure you trust where they’ll be sent.
// tools this server exposes44 tools

These names and descriptions are the publisher's own, read from the source code. We print them as written. Our assessment is the findings above, not this list.

move_mouse

Move the system cursor to absolute coordinates (x, y).

click_mouse

Perform a mouse click.

type_text

Type a string of text into the active window.

press_key

Press a specific key (e.g., 'enter', 'esc', 'tab').

screen_resolution

Return the current primary monitor resolution.

join_meeting

Join a LiveKit room and start publishing the screen as a video track.

leave_meeting

Leave the current LiveKit room and stop screen publishing.

get_status

Return the current remoting substrate status.

conference_schedule

Schedule a new conference.

conference_get

Fetch a single scheduled conference by ID.

conference_list

List conferences with optional filters.

conference_update

Update mutable fields on a scheduled conference. Only non-empty / non-zero args are applied.

conference_cancel

Cancel a scheduled or active conference.

conference_upcoming

List SCHEDULED conferences in the next N days (default 7).

participant_invite

Invite a participant to a scheduled conference.

participant_list_invited

List all invited participants for a scheduled conference.

participant_remove_invited

Remove a participant invitation from a scheduled conference.

get_dev_stats

Get granular local development statistics. SOTA Industrial standard.

query_system_logs

Query Windows System logs for specific patterns with SOTA filtering.

sample_log_analysis

Iteratively sample and analyze system logs for anomaly detection and root cause analysis.

get_substrate_heartbeat

Perform deep heartbeat analysis of LiveKit and Ollama substrates.

orchestrate_industrial_diagnostics

Execute a full-stack industrial diagnostic pass. SOTA-2026 methodology.

orchestrate_remote_support

Orchestrate Remote Support via native Windows Remote Desktop or RustDesk.

sample_system_forensics

Leverage AI sampling to perform deep forensics on system anomalies. SOTA agentic workflow.

generate_meeting_summary

Summarize the meeting transcript and persist to the memory substrate.

extract_action_items

Extract action items and tasks from the meeting transcript.

set_translation_language

Set the target language for live translation in the current session.

room_create

Create a LiveKit room.

room_list

List all active LiveKit rooms.

room_delete

Delete a LiveKit room by name. Kicks all participants.

room_update_metadata

Update the metadata string on a LiveKit room.

room_participant_list

List all live participants currently in a LiveKit room.

room_participant_kick

Kick (remove) a participant from a live LiveKit room.

room_participant_mute

Mute or unmute a participant's track in a live LiveKit room.

room_send_data

Send a data message to a LiveKit room or specific participants.

list_active_conferences

List active LiveKit rooms and scheduled conferences.

notify_conference_active

Notify the grid that a conference is active. SOTA inter-agent signaling.

inter_agent_ping

Broadcast a protocol-compliant heartbeat to other SOTA servers in the grid.

search_contacts

Search the user's address book for contact information.

search_knowledge_base

Search the knowledge base for repository context or history.

meeting_intelligence_summary

Generate a summary of the current meeting and persist it.

analyze_discourse

Analyzes discourse for semantic dilution or jargon overflow.

request_remote_access

Requests proactive remote assistance. Use when the user is struggling with technical tasks.

list_mcp_tools

List all MCP tools discovered from connected servers.

// known CVEs in dependencies1 medium1 low

Disclosed vulnerabilities in this server's declared npm dependencies (via OSV). Whether each is reachable depends on the installed versions.

mediumturbo@2.7.6GHSA-hcf7-66rw-9f5r

Turbo: Login callback CSRF/session fixation

lowturbo@2.7.6GHSA-3qcw-2rhx-2726

Turbo: Unexpected local code execution during Yarn Berry detection

Depend on this server? Get alerted when its CVEs change.Watch this server free →
// environment variables
To run this server yourself, you supply these values. They go in your own MCP client configuration and stay on your machine. The secret label means the value is sensitive, not that the server mishandles it.
configMCP_BRIDGE_URLS
configMCP_PORT
configMCP_HOST
configHEALTH_PORT
configMCP_CENTRAL_DOCS
configAGENT_MODE
configOLLAMA_BASE_URL
configCLOUD_STT_PROVIDER
configMUSE_TRANSCRIBE_MODEL
configMUSE_TRANSCRIBE_BASE_URL
🔐 secretMETA_API_KEY
🔐 secretOPENAI_API_KEY
🔐 secretDEEPGRAM_API_KEY
configLIVEKIT_URL
🔐 secretLIVEKIT_API_KEY
🔐 secretLIVEKIT_API_SECRET
configTELECONF_DATA_DIR
configCOMMS_MCP_URL
configCOMMS_TELEGRAM_CHAT_ID
Deployment configuration, supplied by whoever hosts the server. Users are not asked for these.
deployPORT
// quality suggestions

Tool annotations

No tools have read-only/destructive annotations

Add readOnlyHint or destructiveHint annotations to every tool so hosts can warn users before invoking.

All four hints declared on every tool

44/44 tools missing one or more hints — move_mouse (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); click_mouse (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint); type_text (missing: readOnlyHint, destructiveHint, idempotentHint, openWorldHint), +41 more. OpenAI's directory rejects tools where any of the four hints are missing or non-boolean.

For every tool, set all four hints (readOnlyHint, destructiveHint, idempotentHint, openWorldHint) to explicit true/false values that match the handler’s actual behaviour.

Descriptions match behaviour

2 tools describe read intent but their handlers mutate — get_dev_stats (line 28: git_branch = subprocess.run(["git", "branch", "--show-current"], capture_output=True, text=True).std); query_system_logs (line 87: proc = subprocess.run(["powershell", "-Command", cmd], capture_output=True, text=True, check=True))

Rename the tool, rewrite the description, or move the side-effect into a separate clearly-named tool.

Domain consistency

npm scope @fleet doesn't match GitHub owner sandraschi

Use the same org name across GitHub, npm, and your homepage so users can verify the publisher.

Tool description accuracy

get_dev_stats: description implies read-only but handler writes/deletes/executes; query_system_logs: description implies read-only but handler writes/deletes/executes

Update tool descriptions to accurately reflect all capabilities — especially write, delete, or execute operations.

Claim the listing to review these findings one by one and send us a correction where you disagree, straight to the team. Claiming also means we tell you when the grade moves, and reach you first if we find anything urgent.

// full audit trail
The findings above are the summary. The full trail, every check we ran, each deduction, the network hosts observed and the dependency advisories, goes to verified publishers, along with an alert whenever a new one lands. Verified publishers can also review each finding and dispute it in one click. Publisher corrections have sharpened several of our checks this month, because the maintainer knows the codebase better than any scanner.
// improvement guidance — verified publishers only
We have 5 concrete improvements we can share with the publisher of this MCP. Each comes with specific guidance to raise the trust score.
// embed badge in your README
[![M8ven Verified](https://m8ven.ai/badge/mcp/sandraschi/teleconference-mcp?variant=verified)](https://m8ven.ai/mcp/sandraschi/teleconference-mcp)
Shows verification status without the grade. Want the grade badge instead? Remove ?variant=verified from the URL.
commit: d437fbeefd81687dad46d9d2369a9d3d03666082
code hash: 5dc9c38010a160b71e681824fe695b3cb309b0931249c38d23f6f3f8a70501b3
view raw JSON →
Check MCPs from inside your assistant
Tool Check · MCP

Vetting this one by hand? Tool Check is an MCP that scores other MCPs. Add it once and ask Claude, ChatGPT, or any MCP client to grade a server, surface CVEs, check the publisher, and suggest safer alternatives — before you install.

https://m8ven.ai/api/mcp/tool-check
check_toolsearch_toolscompare_toolsrecommend_alternativescheck_publisherreport_concern
How to add it →Free · no account needed · works in any MCP client