packetfabric-mcp
OfficialThis server has a remotely hosted endpoint. Open its connector listing for connection details, authentication requirements, and setup instructions:
packetfabric-mcp
MCP server for the PacketFabric API, built from its OpenAPI spec
(346 operations, bundled in src/packetfabric_mcp/data/openapi.yaml).
Instead of one tool per endpoint (which overwhelms the model), it exposes 16 tools:
Tool | What it does |
| Current customer account — good credential check |
| Ports / LAGs / cloud ports |
| Virtual circuits (backbone, cloud, IX, marketplace) |
| PTP services |
| Cloud Routers and their connections |
| L2 hosted / dedicated cloud connections |
| POPs / data centers |
| List pricing (MRC/NRC) between locations |
| bps/pps time series for a port or a VC on a port |
| Current/upcoming maintenance by POP or market |
| Reach any other endpoint in the spec |
Safety
Read-only by default. Any POST/PUT/PATCH/DELETE is refused unless the server runs with
PF_ALLOW_WRITES=true.With writes enabled, a write call returns a dry-run preview first; it only executes when re-called with
confirm=true.Auth/session, MFA, signup and API-key-management endpoints are never exposed.
List responses are capped (
max_items, default 100) and can be trimmed to specificfields.
Setup
Requires uv (brew install uv).
cd ~/Documents/src/packetfabric/mcp
uv sync
uv run pytest # offline testsGet an API key in the PacketFabric portal (Settings → API Keys). API keys work with MFA-enabled accounts; login/password does not.
Claude Code
claude mcp add packetfabric -s user -e PF_TOKEN=your-key -- \
uv run --directory ~/Documents/src/packetfabric/mcp packetfabric-mcpClaude Desktop / Cowork
Settings → Developer → Edit Config (~/Library/Application Support/Claude/claude_desktop_config.json):
{
"mcpServers": {
"packetfabric": {
"command": "/opt/homebrew/bin/uv",
"args": ["run", "--directory", "/Users/chad/Documents/src/packetfabric/mcp", "packetfabric-mcp"],
"env": { "PF_TOKEN": "your-key" }
}
}
}(Use which uv for the command path. Restart Claude after editing.)
To allow provisioning, add "PF_ALLOW_WRITES": "true" to env. Consider a separate server entry
(e.g. packetfabric-rw) so read-only stays the default.
Related MCP server: GCP Infrastructure MCP Server
Configuration
Env var | Purpose |
| API key (sent as Bearer). Preferred. |
| Alternative to |
|
|
| Resellers: customer UUID sent as |
| Override base URL (default |
| Use a different OpenAPI file |
| HTTP timeout (s, default 60) and response size cap (default 60000) |
Hosted mode (MCP over HTTP + A2A + discovery)
uv sync --extra a2a
PF_PUBLIC_URL=https://mcp.example.com uv run packetfabric-mcp --http --host 0.0.0.0 --port 8765
# or: docker build -t packetfabric-mcp . && docker run -p 8765:8765 -e PF_PUBLIC_URL=... packetfabric-mcpPath | What |
| MCP streamable HTTP (stateless, so it scales horizontally) |
| MCP Server Card (SEP-2127) |
| A2A v1.0 Agent Card |
| A2A JSON-RPC endpoint |
| AI Catalog listing both cards |
| Same agent card at the pre-0.3 A2A path, for older clients |
| Summary and links for language models (llmstxt.org) |
| Short human-readable page linking to all of the above |
| Liveness |
Every caller uses their own PacketFabric API key, sent as Authorization: Bearer <key> (plus
On-Behalf: <customer uuid> for resellers). The operator's PF_TOKEN/PF_LOGIN are ignored in HTTP mode
unless PF_HTTP_USE_SERVER_CREDENTIALS=true, which is only safe for a private single-user deployment.
Put it behind TLS; the discovery documents are public by design and contain no secrets.
The A2A agent is deterministic, not an LLM: send a DataPart {"skill": "list_ports", "arguments": {"pop": "LAX1"}}
and get the API result back as a JSON data artifact. Skills mirror the MCP tools (see the agent card).
A2A access is always read-only. A2A tasks are private to the API key (and On-Behalf customer) that created
them; requests without a key get a plain reply and nothing is stored.
curl -s https://mcp.example.com/a2a -H 'A2A-Version: 1.0' -H 'Content-Type: application/json' \
-H "Authorization: Bearer $PF_TOKEN" -d '{"jsonrpc":"2.0","id":1,"method":"SendMessage","params":{"message":
{"messageId":"1","role":"ROLE_USER","parts":[{"data":{"skill":"find_locations","arguments":{"market":"NYC"}}}]}}}'Env var (HTTP mode) | Purpose |
| Public https base URL advertised in the cards (otherwise derived from the request) |
|
|
|
|
| Icon advertised in the cards |
| Request body cap for non-MCP routes, including |
| How long finished A2A tasks stay retrievable (default 3600) |
| Caps on stored A2A tasks, oldest evicted first (defaults 10000 / 200) |
Domain-level discovery: if the server runs on its own host (e.g. mcp.packetfabric.com), the
/.well-known/ documents are already in the right place. To advertise it from the main domain, serve a copy of
/.well-known/ai-catalog.json from https://packetfabric.com/.well-known/ai-catalog.json (the entries hold
absolute URLs, so a static copy works).
Publishing
Listed on the MCP Registry as
io.github.PacketFabric/packetfabric-mcp (see server.json), installed from PyPI as packetfabric-mcp.
Branches: dev (default) takes every change. Each push to it publishes the container image
ghcr.io/packetfabric/public-mcp:vX.Y.Z-dev.N (.github/workflows/image.yml), and the staging server at
https://mcp.dev.packetfabric.net picks the newest one up within minutes. main is the release line.
Bump the version in
pyproject.toml,src/packetfabric_mcp/__init__.pyandserver.json(tests fail if they disagree).Merge
devintomainwith a PR, then push a tagvX.Y.Zonmain..github/workflows/publish.ymlruns the tests, publishes to PyPI (Trusted Publishing), then publishesserver.jsonto the MCP Registry using GitHub OIDC..github/workflows/image.ymlpublishesghcr.io/packetfabric/public-mcp:vX.Y.Zand writes its digest to the run summary. Both refuse a release tag that is not onmain; pre-release tags (vX.Y.ZrcN) may come fromdev, publish to PyPI only (not the MCP Registry), and build no image.Production (
https://mcp.packetfabric.com) runs the newest release: it picks up the newvX.Y.Zimage within minutes ofimage.ymlpublishing it. Pushing a release tag onmainis therefore a production deploy.The registry entry lists the hosted endpoint
https://mcp.packetfabric.com/mcp(inserver.json; the repo variableMCP_PUBLIC_URLoverrides it if set).
One-time: add a PyPI Trusted Publisher for packetfabric-mcp (repo PacketFabric/public-mcp, workflow
publish.yml, environment pypi). The mcp-name: comment at the top of this README is how the registry verifies
that the PyPI package belongs to this server; keep it.
To publish under com.packetfabric/... instead of io.github.PacketFabric/..., change REGISTRY_NAME in
metadata.py and server.json, add the DNS TXT record from mcp-publisher login dns, and switch the
workflow's login step.
Other
Refresh the bundled spec:
uv run packetfabric-mcp --update-specTo add a curated tool, copy one of the
pf_list_*functions inserver.pyand point_run()at anoperation_id(find one withpf_search_endpoints). Add a matching entry toSKILLSina2a_agent.py.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Create, manage, and query your Google Cloud SQL resources.
Provides capabilities that let LLM agents perform a range of infrastructure management tasks.
Read-only AI/LLM cost tools with current MCP discovery and attributable Registry transport.
Provides read access to your GKE and Kubernetes resources.
Related MCP Servers
- AlicenseCqualityDmaintenanceProvides tools and context for interacting with Google Cloud services, enabling natural language management of billing, monitoring, logging, IAM, Spanner, and more.56197 npmApache 2.0
- FlicenseNot gradedqualityDmaintenanceProvides 30+ read-only tools for querying Google Cloud Platform infrastructure, designed for AI assistants and Terraform workflows.-
- FlicenseNot gradedqualityCmaintenanceEnables managing Netris network fabric through natural language, including VPCs, BGP sessions, load balancers, NAT rules, IPAM, and other network operations.-
- AlicenseNot gradedqualityCmaintenanceProvides read-only MCP tools that let an LLM client query network inventories, inspect devices over SSH, and diagnose network conditions such as interfaces, routes, BGP, OSPF, and VPN state. Configuration changes stay in the local CLI, while the MCP surface remains strictly read-only.Apache 2.0