@taskbullet/mcp-server

MCPcommunitylive
v0.2.0TaskBulletMITUpdated 1d agonpmGitHub

MCP server for delegating tasks and US/CA phone calls from AI agents (Claude, Cursor, OpenClaw, Grok) to real human virtual assistants. Stdio and streamable HTTP.

Endpoint healthlive
checked 3 days ago · 109ms · auth required
100% of the last 1 check reached this endpoint
Works in
ClaudeCursorCopilotChatGPTGemini

Inferred from the transports this listing declares (stdio, streamable-http). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
277Downloads/wk
1d agoLast update
Needs 1 credential before it runs
  • TASKBULLET_API_KEYAPI keyrequired

    TaskBullet API key (tb_live_...)

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
AuthorTaskBullet
LicenseMIT
Version0.2.0
Sourcenpm+mcp-registry
Trust Status
B
60/100Good
✓Listed in Forge index+10/10
—Publisher identity verified+0/20
→ Publisher: run `forge publish` from the package repo to claim ownership
—Ed25519 publish signature+0/5
→ Included automatically when the publisher runs `forge publish`
—Domain verification+0/5
→ Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
—npm Trusted Publishing (Sigstore)+0/5
→ Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
—npm maintainer match+0/5
→ Earned once your identity is verified above and that login is an npm maintainer of this package
✓CVE scan · clean+30/30
✓Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain—
Provenance—
Dependencies✓ 60 resolved+ · none vulnerable
Tool surface13 tools · none privileged
Security scan✓ Cleanv0.2.0 · todayHow well does this scan work?
EvalsNone
IndexedOct 17, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

13 tools · none privileged
Statically extracted from the published packagev0.2.0 · 4h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

get_balanceNo description published

This tool published no description. Forge does not invent one.

delegate_taskNo description published

This tool published no description. Forge does not invent one.

list_tasksList recently delegated tasks for this account (id, title, status, short result). awaitingCustomerConfirm true means the delivery is done and the human must confirm, cancel, or reopen. amNote is the delivery note and deliverableLinks are https links from that note. pending and in_progress omit cust…

List recently delegated tasks for this account (id, title, status, short result). awaitingCustomerConfirm true means the delivery is done and the human must confirm, cancel, or reopen. amNote is the delivery note and deliverableLinks are https links from that note. pending and in_progress omit cust…

No input schema was published for this tool.

get_taskGet the current status, title, completion timestamp, and full result notes for a specific delegated task. awaitingCustomerConfirm true means ask the human, then confirm_task, cancel_task, or reopen_task. amNote is the AM or VA note. deliverableLinks lists https links. Stop when status is completed,…

Get the current status, title, completion timestamp, and full result notes for a specific delegated task. awaitingCustomerConfirm true means ask the human, then confirm_task, cancel_task, or reopen_task. amNote is the AM or VA note. deliverableLinks lists https links. Stop when status is completed,…

No input schema was published for this tool.

confirm_taskAccept a delivery that is awaitingCustomerConfirm. Settles tracked hours, releases the board and ledger hold, and marks the task completed. If the human does not respond, the job confirms itself after 3 days. Ask the human first. Idempotency-Key is required. A repeat of the same key returns the sam…

Accept a delivery that is awaitingCustomerConfirm. Settles tracked hours, releases the board and ledger hold, and marks the task completed. If the human does not respond, the job confirms itself after 3 days. Ask the human first. Idempotency-Key is required. A repeat of the same key returns the sam…

No input schema was published for this tool.

cancel_taskCustomer never mind. Releases the hold and bills only tracked time. Does not send the completion webhook. Ask the human first. Idempotency-Key is required.

Customer never mind. Releases the hold and bills only tracked time. Does not send the completion webhook. Ask the human first. Idempotency-Key is required.

No input schema was published for this tool.

reopen_taskSend a delivery that is awaitingCustomerConfirm back to the account manager with a reason. Does not settle hours. Ask the human first. Idempotency-Key is required.

Send a delivery that is awaitingCustomerConfirm back to the account manager with a reason. Does not settle hours. Ask the human first. Idempotency-Key is required.

No input schema was published for this tool.

place_callNo description published

This tool published no description. Forge does not invent one.

validate_callCheck a phone-call body without creating a call or placing a hold. Same fields as place_call, without idempotencyKey. A ready body includes hold_cents for the full call (tier 1 default $5 at 5 minutes) and whether recipient_timezone was inferred.

Check a phone-call body without creating a call or placing a hold. Same fields as place_call, without idempotencyKey. A ready body includes hold_cents for the full call (tier 1 default $5 at 5 minutes) and whether recipient_timezone was inferred.

No input schema was published for this tool.

get_callRead one human phone call, including needs_info missing_fields or the final result.

Read one human phone call, including needs_info missing_fields or the final result.

No input schema was published for this tool.

update_callFill missing_fields on a call in needs_info. Same result shapes as place_call.

Fill missing_fields on a call in needs_info. Same result shapes as place_call.

No input schema was published for this tool.

cancel_callCancel a call before the first dial and release the hold. After dialing, the current attempt finishes.

Cancel a call before the first dial and release the hold. After dialing, the current attempt finishes.

No input schema was published for this tool.

get_transcriptRead transcript.txt for one call. A cancelled call returns call_cancelled. An empty transcript returns transcript_not_ready.

Read transcript.txt for one call. A cancelled call returns call_cancelled. An empty transcript returns transcript_not_ready.

No input schema was published for this tool.

10 of 13 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

MCP server for delegating tasks and US/CA phone calls from AI agents (Claude, Cursor, OpenClaw, Grok) to real human virtual assistants. Stdio and streamable HTTP.

Keywords
mcpmcp-servermodel-context-protocolclaudecursoropenclawanthropicai-agentai-agent-handoffhuman-in-the-loopvirtual-assistantvataskbullettask-delegationphone-callsagent-toolsai-toolsllm-toolsautonomous-agent
Alternatives
Comparing tool surfaces…

Dependency tree

What one Forge scan resolved from npm metadata on 2026-10-21 — observed resolution, not a publisher declaration.

60 packages resolved · 2 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

The crawl stopped at the depth-4 limit. Anything below that level was never resolved.

The crawl stopped at the 60-package limit. The rest of the tree was never resolved.

36 more resolved packages are not drawn here (display cap: 24). Every dependency carrying an advisory is drawn regardless of the cap. Full inventory (CycloneDX SBOM)

Declared but not resolved

55 declared dependencies never landed in the tree. They are missing from Forge's resolution, not from the package.

+43 more not listed. The counts by reason above cover all of them.

Not followed: peerDependencies. This tree covers runtime dependencies only, so anything those pull in was never resolved.