mcpulse
Server Details
Analytics for MCP servers. Query your tool calls, first-call success, retries and schema cost.
Glama couldn't complete the latest health check. If this server requires authentication, missing or expired test credentials may be the cause. A test profile lets Glama authenticate for health checks and discover tools; it is separate from your personal connections.
If you are the author, claim ownership, then add or update a test profile under Admin → Test Profile.
- Status
- Unhealthy
- Uptime
- 9.8% over 21 days
- OAuth
- Works in Glama
- Last Tested
- Transport
- Streamable HTTP
- URL
TDQS
Scored across 33 tools
Every tool is anchored to a distinct resource-action pair (MCPs, keys, alerts, channels, team, analytics), and descriptions explicitly disambiguate near-neighbors like get_mcp vs get_overview vs get_insights and list_alerts vs list_alert_firings. I see no pair where an agent would plausibly guess the wrong tool for the same task.
All tools follow a consistent verb_noun snake_case pattern: create_, get_, list_, update_, delete_, rename_, revoke_, invite_, remove_, change_, set_, mark_. There are no mixed conventions or vague verbs.
At 33 tools, the surface is well above the 25+ threshold for 'too many' and far from the 3-15 sweet spot. Even though each tool is individually purposeful, the size imposes real navigation cost and several workflows still intentionally hand off to the dashboard.
The domain is covered broadly: MCP lifecycle, team management, alerts, digests, and analytics all have solid read/update or CRUD coverage. Minor gaps exist—ingest keys cannot be created, Slack/Discord connections cannot be configured, and nothing is delivered yet—but these are documented dashboard hand-offs rather than fatal omissions.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
33 tool updates
- First observed
change_member_role - First observed
create_alert - First observed
create_mcp - First observed
delete_alert - First observed
delete_mcp - First observed
get_account - First observed
get_channels - First observed
get_company - First observed
get_digest - First observed
get_inbox - First observed
get_insights - First observed
get_mcp - First observed
get_overview - First observed
get_profile - First observed
get_sessions - First observed
get_tool - First observed
get_usage - First observed
invite_member - First observed
list_alert_firings - First observed
list_alerts - First observed
list_keys - First observed
list_mcps - First observed
list_members - First observed
list_tools - First observed
mark_inbox_read - First observed
remove_member - First observed
rename_mcp - First observed
revoke_key - First observed
set_digest - First observed
update_alert - First observed
update_channels - First observed
update_company - First observed
update_profile
Publisher details
- Operator
- MCPulse · Publisher source
- Operator website
- https://getmcpulse.com · Publisher source
- Vendor relationship
- First-party · Publisher source
- Documentation
- https://docs.getmcpulse.com/mcp/connect · Publisher source
- Trust center
- Not available
- Restrictions
- Requires a free MCPulse account. Sign-in is OAuth, so no API key needs to be created or stored. The free tier covers one server. The MCP server returns your own account's data, so it is only useful once you have at least one MCP server instrumented with the MCPulse SDK. No admin approval, no regional limits, no custom OAuth app required. · Publisher source
Related MCP Connectors
- AgentCatOAuthcom.agentcat
Analytics and debugging for your MCP server — explore usage and sessions, then root-cause errors.
Read-only analytics for Convex apps, queryable via MCP from Claude, Cursor, and other clients.
Analytics your AI agent can actually use. Track, experiment, and optimize via MCP.
- SpanlyOAuthcom.spanly
MCP observability. Query live traffic, errors, duration, and alerts from your AI agent.
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceA Python utility for adding usage tracking, analytics, and audit trails to MCP servers using SQLite-backed persistence. It enables developers to monitor tool, prompt, and resource activity and expose these statistics directly to LLM clients.4MIT
- AlicenseAqualityDmaintenanceMCP server for querying OpenAI usage and cost data, including spend summaries, daily breakdowns, month-over-month comparisons, and token usage by model.3MIT
- FlicenseNot gradedqualityBmaintenanceMCP server that wraps Nightjar's analytics API, enabling Claude Code to query events, funnels, dashboards, and metrics through natural language.-
- FlicenseNot gradedqualityCmaintenanceEnables sharing MCP servers with clients, storing tool calls in PostgreSQL, and providing usage analytics via an admin dashboard and API.-
Glama MCP Gateway
Add one secure layer between your agents and this server.