DeployIt Product Expert
AI product expert answering from live source code, with sources and a verification status.
Early AccessEvery agent is free to connect — no card, no checkout.
We use essential cookies to keep you signed in. With your consent we also use non-essential cookies for analytics. Read our privacy policy
MCP Servers › Honeycomb MCP

Query telemetry, run BubbleUp, read traces, and manage Boards, Triggers and SLOs.
A preview derived from this server’s definition — not a live run. Nothing runs and no key is sent until you connect. You connect directly to the provider’s own server with their sign-in.
Team name, current time, environments.
One environment, its datasets and fields.
Dataset metadata and full column schema.
Column schema with optional sample values.
Run a time-series aggregation query.
Results of a previous run.
Search query history and saved queries by intent.
Find columns by intent across datasets.
BubbleUp differential analysis.
All spans for a trace, as a waterfall.
Span names ranked by count.
Attribute summary for a span name.
Service dependencies (Enterprise only).
Anomaly-detection profiles.
Search the semantic-convention registry.
Full attribute definitions.
Top-level semconv namespaces.
List Boards.
Create a Board.
Update a Board.
Read Triggers.
Create a Trigger.
Update a Trigger.
Read SLOs.
Create an SLO, auto-creating its SLI column.
Update an SLO.
Notification destinations.
Add a notification destination.
Send a message to the Canvas agent.
Poll the Canvas agent for a reply.
Other agents gen_ai telemetry.
Full event timeline for one conversation.
Refinery documentation.
Send feedback to Honeycomb.
Used with: mcp.honeycomb.io, mcp.eu1.honeycomb.io
Honeycomb MCP is a remote MCP server. Add its URL to any MCP-capable client — FindAgent lists it; it runs on the provider's own infrastructure.
https://mcp.honeycomb.io/mcpChatGPT (Plus / Pro): Settings → Connectors → add a remote MCP server, then paste the URL and approve it.
You add this server inside your client and approve it once — that in-client step is a security check, so there's no one-click button for it.
You give these to the server itself when it signs you in. They never pass through FindAgent, so we neither store them nor control where they go.
AI product expert answering from live source code, with sources and a verification status.
cotal.ai actions: product overview, site search, build log, feedback, Cloud waitlist, updates, calls
Front desk for the AIS MCP campus: lists our buildings (CVE, Flight Recorder), prices, how to pay
Find, create, and update Linear issues, projects, and comments.