BigPanda MCP server: your action plans become the tools

Why this connector's inventory is different in every organization, what one shared input schema means for an agent, and how BigPanda consumes your servers in the other direction.

Last verified 1 September 2026 · from The BigPanda public API spec, its docs and the live endpoint

This page is one of 90 in a directory of monitoring and developer tools. Each page checks what an AI coding agent can get out of the tool through its MCP server, the connector that lets the agent query the tool directly.

What is the BigPanda MCP server?

BigPanda correlates alerts into incidents. Biggy is its AI assistant, and an action plan is a configured piece of work Biggy knows how to do, such as troubleshooting an issue from historical data.

The MCP endpoint exposes those action plans. An external agent lists them, picks one from its description, and sends it a question in English. The action plan does the work and answers.

That is a different shape from every other connector in this directory. Elsewhere a tool is an API call with typed parameters. Here a tool is another agent, and the parameter is a sentence.

BigPanda sits on both ends of MCP:

The two are configured in different places and answer different questions. A search result about connecting an MCP server to Biggy is the client direction, not this endpoint.

BigPanda's subject is the incident. Its reach depends on which action plans you have enabled.

In practice, BigPanda answers incident questions at whatever depth its action plans were built for. Two organizations connecting the same endpoint can get entirely different tool lists.

What can an AI agent do with BigPanda?

There is no fixed tool list to publish, and that is the design. Every Biggy action plan your organization has enabled becomes one MCP tool, so the surface is whatever your own plans cover. Each tool takes a query in English, and its description is derived from the plan behind it. An agent can ask incident questions your organization has already modelled, and nothing beyond them.

BigPanda MCP server limits: where answers come back incomplete

BigPanda's first limitation is unusual. You cannot know its tool list before you connect.

How to configure BigPanda MCP for agents

1. 1

   Audit the action plans before connecting

   They are the tool list. Whatever is enabled is what an external agent can see and call.

2. 2

   Expect stateless HTTP

   A single /mcp endpoint handles initialize, tools/list and tools/call over POST. GET and DELETE return 405, because there are no sessions and no server-sent event streams.

3. 3

   Decide the reasoning effort deliberately

   Every tool accepts low, medium or high, and the default is not stated in the specification.

4. 4

   Write the whenToSelect field carefully

   It is not internal documentation. It becomes part of the tool description an external agent reads when choosing.

5. 5

   Keep the client direction separate

   Adding an MCP server to Biggy is a different feature, configured in the web app, with its own trust policy.

Paste this into your agent’s instructions

A tool here is an action plan, which is itself a model doing work. Two layers of inference between the question and the alert data is worth stating.

When you answer using BigPanda MCP tools, state:
- Which action plan you called, and the query text you sent
  it. The tool takes free text, so the wording matters.
- That the answer came from an action plan rather than from
  a direct query against alert data.
- The reasoning effort you requested, if you set one.
Never state that data does not exist. State the action plan
you called and what it returned.
Write your answer in ASD-STE100 Simplified Technical
English. Use short sentences with one idea in each.

Do you need the MCP server at all?

Not for anything that runs on a timer. The alert and incident endpoints of the BigPanda API take typed parameters, and they are the direct route for a report you already know how to shape.

For alert correlation without the action plan layer, PagerDuty and Opsgenie expose incident data as structured tools instead of as prose.

Where the question is about metrics rather than incidents, Datadog, Grafana and Prometheus answer it far more cheaply.

BigPanda also publishes an A2A interface for its Alpha agent, using JSON-RPC 2.0 for messages, streamed responses and task status. That is the route for agent-to-agent work rather than tool calls.

With MCP, work your team has already configured becomes callable from outside, without rebuilding any of it as an API integration.

Call tools/list first. The answer is your own configuration, and nobody else's page can tell you what it says.

BigPanda MCP server setup

Nothing is installed. The endpoint is https://api.biggy.io/mcp, and the whole MCP lifecycle runs over HTTP POST against that single path.

Every block below carries a BigPanda bearer token. The specification states that all BigPanda APIs require bearer token authorization in the call headers.

The tool list you get is your own. Each enabled action plan becomes one tool, so confirm what is enabled before wiring an agent to it.

claude mcp add --transport http bigpanda \
  https://api.biggy.io/mcp \
  --header "Authorization: Bearer <api-key>"

curl -sS -X POST "https://api.biggy.io/mcp" \
  -H "Content-Type: application/json" \
  -H "Accept: application/json, text/event-stream" \
  -H "Authorization: Bearer <api-key>" \
  -d '{"jsonrpc":"2.0","id":2,
       "method":"tools/list","params":{}}'

{"mcpServers":{"bigpanda":{"type":"http",
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

[mcp_servers.bigpanda]
url = "https://api.biggy.io/mcp"

[mcp_servers.bigpanda.headers]
Authorization = "Bearer <api-key>"

Every other client

Each block below is the configuration for one client, with the file path and the key that client expects.

{"mcpServers":{"bigpanda":{"command":"npx",
  "args":["-y","mcp-remote","https://api.biggy.io/mcp",
    "--header","Authorization: Bearer ${TOKEN}",
    "--transport","http-only"],
  "env":{"TOKEN":"<api-key>"}}}}

{"mcpServers":{"bigpanda":{
  "httpUrl":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"servers":{"bigpanda":{"type":"http",
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"mcpServers":{"bigpanda":{
  "serverUrl":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"context_servers":{"bigpanda":{
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"mcpServers":{"bigpanda":{"type":"http",
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"amp.mcpServers":{"bigpanda":{
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"mcpServers":{"bigpanda":{"type":"streamableHttp",
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

extensions:
  bigpanda:
    type: streamable_http
    uri: https://api.biggy.io/mcp
    headers:
      Authorization: Bearer <api-key>

{"mcpServers":{"bigpanda":{"command":"npx",
  "args":["-y","mcp-remote","https://api.biggy.io/mcp",
    "--header","Authorization: Bearer ${TOKEN}",
    "--transport","http-only"],
  "env":{"TOKEN":"<api-key>"}}}}

{"mcpServers":{"bigpanda":{
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"mcpServers":{"bigpanda":{"type":"http",
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"mcpServers":{"bigpanda":{
  "type":"streamable-http",
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

name: BigPanda
version: 0.0.1
schema: v1
mcpServers:
  - name: bigpanda
    type: streamable-http
    url: https://api.biggy.io/mcp
    requestOptions:
      headers:
        Authorization: Bearer <api-key>

{"mcpServers":{"bigpanda":{
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

{"mcpServers":{"bigpanda":{"type":"http",
  "url":"https://api.biggy.io/mcp",
  "headers":{"Authorization":"Bearer <api-key>"}}}}

Integrations  ->  + Add MCP
  Service Type:   Observability | ITSM | Context Retrieval
  MCP Server URL: https://your-server.example.com/mcp
  Bearer Token:   <token Biggy uses to call your server>
  Deployment:     Cloud | On Prem
  Trust Policy:   Allow only selected tools (recommended)

Read-only access, permissions and security

• Your action plans are the attack surface, in both directions

  Anything enabled becomes callable, and the description an external agent reads is generated from fields your own team wrote.

• Free text is the only parameter

  There is nothing to validate at the schema level: an agent sends a sentence, and the action plan decides what to do with it.

• In the client direction, prefer the allowlist

  BigPanda offers two trust policies. Allow only selected tools is the one it marks as recommended, and new tools then need explicit approval. Auto-trust all tools allows every tool the server exposes, including ones added later.

• The on-prem option crosses your firewall deliberately

  Marking an integration as on-prem makes it eligible for the Biggy Relay Client, which is how it reaches internal infrastructure.

• The token is a full BigPanda API key

  The specification states that all BigPanda APIs require bearer token authorization, so the credential is not scoped to MCP alone.

Troubleshooting

`405 Method Not Allowed`

Only POST is supported. The specification states that GET and DELETE return 405, because stateless mode uses neither sessions nor server-sent event streams.

`tools/list` returns nothing useful

The list is your enabled action plans. If it is short or empty, the answer is in the BigPanda action plan configuration, not in the client.

The agent picks the wrong action plan

Tool descriptions are generated from each plan's description and whenToSelect fields. Rewriting those fields is the supported way to change how an external agent chooses.

Answers are shallow or too slow

Every tool accepts a reasoningEffort of low, medium or high. It is optional, so a client that omits it takes whatever the server defaults to.

The response is hard to parse

Set responseFormat to plain-text. The default documented in the schema table is markdown.

Biggy cannot reach your internal server

Set the deployment type to On Prem. That marks the integration as eligible to connect through the Biggy Relay Client, which is the documented route to infrastructure behind a firewall.

BigPanda MCP server: Reference

What the vendor documents

The facts below come from BigPanda's own API specification and its MCP integration documentation, read 25 August 2026. No tool count can exist, because the inventory is per organization. Public discussion of the endpoint is thin.

“Each enabled action plan in your organization becomes an MCP tool. Tool descriptions are derived from the action plan's description and whenToSelect fields, giving external agents enough context to choose the right tool autonomously.”

“Allow only selected tools (Recommended): Pick exactly which tools Biggy can call. New tools require explicit approval.”

“GET and DELETE calls return 405 Method Not Allowed (stateless mode does not use sessions or server-sent event (SSE) streams).”

The BigPanda public API specification and the MCP integration documentation were read on 25 August 2026, and the endpoint was probed on the same date. No tool count is claimed, because the specification states the inventory is per organization.

Should you connect an agent to BigPanda?

Yes. Best for incident questions phrased in English, against action plans you have reviewed.

Strongest fit

BigPanda customers who have already built action plans and want external agents to reach them.

Main advantage

Work that already exists becomes callable without building an integration for each capability.

Main weakness

Nothing about the tool list is knowable in advance, because it is generated from your own configuration.

Operational risk

Free text is the only input, so nothing is validated before an action plan acts on it.

Frequently asked questions