← Back to search

@getpromptly/mcp-server

GitHub Actions Scanned 25d ago

MCP server for tracking AI coding sessions — captures conversations, token usage, and costs

npm ↗
D
40 / 100

Versions

0.1.16latest
Jul 5, 2026
0.1.15
Jun 10, 2026
0.1.14
Jun 10, 2026
0.1.13
Jun 10, 2026
0.1.12
May 10, 2026
+ show 7 moreshow less
0.1.11
Feb 17, 2026
0.1.10
Feb 17, 2026
0.1.7
Feb 5, 2026
0.1.6
Feb 1, 2026
0.1.2
Feb 1, 2026
0.1.1
Feb 1, 2026
0.1.0
Feb 1, 2026
PermissionsTool SafetyAuthAnnotationsCode QualityStabilitySpecVuln HistoryAuthorTransparencyCommunity

Tools 5

promptly_start
annotations: none low

Start logging AI conversations for a ticket

ticketId string
promptly_log
annotations: none low

Log a conversation turn (called automatically during active session)

name string input unknown model string output unknown content string timestamp string tokenCount number
promptly_status
annotations: none low

Check the current logging session status

promptly_finish
annotations: none low

Finish the current logging session

promptly_review
annotations: none low

Review the AI coding sessions behind a GitHub pull request and return a verdict on prompt quality (LLM-as-judge: intent clarity, scope discipline) and spend (token waste, model misuse, avoidable cost). READ-ONLY — call this when the user says they

prNumber number

Permissions 4

network medium
Server uses network capabilities via: fetch()
filesystem low
Server uses filesystem capabilities via: fs sync ops
shell high
Server uses shell capabilities via: child_process, execSync()
env_vars low
Server uses env_vars capabilities via: process.env

Scan Findings 0

No scan findings.