packetfabric-mcp
Officialby PacketFabric
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PF_LOGIN | No | PacketFabric login username. Alternative to PF_TOKEN when used with PF_PASSWORD; supports automatic re-login on 401. | |
| PF_TOKEN | No | PacketFabric API key, sent as a Bearer token. Preferred authentication method. | |
| PF_API_URL | No | Override the PacketFabric API base URL. | https://api.packetfabric.com |
| PF_TIMEOUT | No | HTTP timeout in seconds. | 60 |
| PF_ICON_URL | No | Icon URL advertised in the discovery cards. | |
| PF_PASSWORD | No | PacketFabric login password. Alternative to PF_TOKEN when used with PF_LOGIN. | |
| PF_ON_BEHALF | No | Reseller customer UUID sent as the On-Behalf header. | |
| PF_SPEC_PATH | No | Use a different OpenAPI specification file. | |
| PF_PUBLIC_URL | No | Public HTTPS base URL advertised in the MCP Server Card and A2A Agent Card. Only used in HTTP mode. | |
| PF_DISABLE_A2A | No | Set to "true" in HTTP mode to serve MCP only and disable A2A. | false |
| PF_ALLOW_WRITES | No | Set to "true" to allow create/modify/delete operations. Each write still requires confirm=true. | false |
| PF_A2A_MAX_TASKS | No | Maximum number of stored A2A tasks. Oldest tasks are evicted first. | 10000 |
| PF_MAX_BODY_BYTES | No | Request body size cap in bytes for non-MCP routes, including /a2a. Default is 1 MiB; larger requests receive HTTP 413. | 1048576 |
| PF_MAX_RESPONSE_CHARS | No | Maximum response size cap in characters. | 60000 |
| PF_A2A_TASK_TTL_SECONDS | No | How long finished A2A tasks remain retrievable, in seconds. | 3600 |
| PF_A2A_MAX_TASKS_PER_CALLER | No | Maximum number of stored A2A tasks per caller. Oldest tasks are evicted first. | 200 |
| PF_HTTP_USE_SERVER_CREDENTIALS | No | Set to "true" in HTTP mode to fall back to the operator's own PacketFabric credentials. Only safe for a private single-user deployment. | false |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Server capabilities have not been inspected yet.
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
No tools | |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
This server cannot be deployed
Maintenance
ActivityMaintained
ResponsivenessNo recent community issues