WardenPoint

io.github.WardenPointPublished by GitHub account WardenPointv0.1.2Updated Oct 24, 2026

Configure on-call alerting from an AI agent: recipients, groups, escalation policies, schedules.

Overview

AI-generated overview

Lets an AI assistant configure a WardenPoint on-call alerting account — recipients, groups, escalation policies, schedules and routing — without the dashboard.

What you can do
  • Manage recipients, contacts and groups
  • Configure notification rules, escalation policies and on-call schedules
  • Set up alert-source integrations and routing rules, including telephony
  • Expose one tool per operation of the installation's own OpenAPI description, fetched at startup
  • Report the tool count and token cost at startup, and narrow the tool set with a pattern variable
When to use it
Useful when someone wants an agent to inspect or change on-call alerting configuration — building escalation chains, adding recipients, or explaining an existing setup — instead of clicking through the WardenPoint dashboard.
Requirements
Node 20 or newer, run locally over stdio via npx. Requires WARDENPOINT_BASE_URL (installation origin, no trailing slash or /api/v1) and a company API key in WARDENPOINT_API_TOKEN, sent as X-API-Key; the token is not needed for --list-tools or --spec-report. Optional: WARDENPOINT_TOOLS, WARDENPOINT_TIMEOUT_MS, WARDENPOINT_OPENAPI_PATH, WARDENPOINT_ALLOW_INSECURE_TLS. Network access to the installation is required; there is no offline fallback.
Before you install
The API key grants real configuration abilities chosen at issue time: config.write allows create, update and delete, and notifications.send fires alerts. Start with a read-only key. The full tool set is about 89 tools and roughly 64k tokens of context, so narrow it with WARDENPOINT_TOOLS. WARDENPOINT_ALLOW_INSECURE_TLS disables certificate verification and is for development only. Integration secrets for alert-source webhooks are passed as tool arguments, not stored. Setup steps such as…

Installation

In SourceWeft

  1. Open WardenPoint in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

WardenPoint MCP server

An MCP server that lets an agent configure a WardenPoint account — recipients, contacts, groups, notification rules, escalation policies, on-call schedules, alert-source integrations, routing rules and telephony — without anyone opening the dashboard.

It speaks stdio and exposes one tool per operation of your installation's own OpenAPI description.

json
{  "mcpServers": {    "wardenpoint": {      "command": "npx",      "args": ["-y", "@wardenpoint/mcp-server"],      "env": {        "WARDENPOINT_BASE_URL": "https://wardenpoint.com",        "WARDENPOINT_API_TOKEN": "acb_xxxxxxxx.xxxxxxxx"      }    }  }}

That is the whole installation. Your MCP client starts the server on demand; nothing runs between sessions.

The one rule this server exists to keep

There is no second copy of the contract here.

Every tool — its name, its text, its arguments, their descriptions, their enums and bounds, the responses it can answer with — is read at startup from the OpenAPI description served by the installation you are configuring (GET {WARDENPOINT_BASE_URL}/docs). Nothing about the API is restated in this package.

That is deliberate, and it is why the tools cannot quietly drift:

  • an endpoint added to your installation appears as a tool the next time the server starts — no package upgrade involved;
  • a description reworded upstream rewords the agent's instructions with it;
  • an operation nobody described is invisible to the agent, which is the correct failure and the reason --spec-report exists.

A description bundled inside this package would describe whatever was current when the package was published, while the agent talks to whatever you actually run. There is no offline fallback for the same reason: every tool here is an HTTP call to that installation, so if it cannot be reached, a complete tool list would be a list of things that cannot be done.

Requirements

Node 20 or newer. No build step, no native modules.

Environment

VariableRequiredMeaning
WARDENPOINT_BASE_URLyesOrigin of the installation — no trailing slash, no /api/v1 suffix. The description carries full paths.
WARDENPOINT_API_TOKENto callA company API key from Dashboard → Integrations → API keys. Sent as X-API-Key. Not needed for --list-tools or --spec-report.
WARDENPOINT_ALLOW_INSECURE_TLSno1 disables certificate verification. Development stands only — never against production.
WARDENPOINT_TIMEOUT_MSnoPer-request timeout, default 30000.
WARDENPOINT_TOOLSnoComma-separated patterns limiting which tools are offered, e.g. recipients,groups or v1_schedules_*. Unset means all of them.
WARDENPOINT_OPENAPI_PATHnoRead the description from a local file instead of the installation. For developing against a description that is not deployed yet.

The token is read from the environment at every start and is never written anywhere by this package.

What the key is allowed to do

Abilities are chosen when you issue the key, and a 403 names the one that was missing:

  • config.read — read the whole configuration. A good place to start: the agent can explain an account somebody else built and change nothing.
  • config.write — create, update, delete.
  • notifications.send / notifications.read — fire alerts and inspect them.

No ability can read a secret. There is no such ability in the vocabulary, so it cannot be granted by mistake. The API reports whether a credential is set and whether it verified — never its value.

What the tool list costs

Every tool definition is sent to the model before the person says anything, so it is spent whether or not the conversation ever touches WardenPoint. The full set of 89 tools is roughly 64k tokens — on a 200k context window, a third of it.

The server prints the figure at startup so it is not an invisible cost:

wardenpoint-mcp-server: 89 tools (~63k tokens of context; narrow it with WARDENPOINT_TOOLS) from …

If a session only ever touches part of the product, say so:

json
"env": { "WARDENPOINT_TOOLS": "recipients,groups,schedules" }

That drops the same run to a handful of tools and a few thousand tokens. Patterns match tool names (v1_recipients_store), and * works. Leave it unset and you get everything, which is the safe default: a tool that quietly disappeared looks like a missing product capability.

Running

bash
npx -y @wardenpoint/mcp-server --list-tools     # every tool, with its argumentsnpx -y @wardenpoint/mcp-server --spec-report    # gaps in the description itself

Both talk to WARDENPOINT_BASE_URL to fetch the description; neither needs a token. Without arguments the process speaks MCP over stdio and is meant to be started by a client, not by hand.

Two credentials, and why they are not interchangeable

  • API key (WARDENPOINT_API_TOKEN) — who you are. Every configuration tool uses it.
  • Integration secret — proves a specific alert-source webhook is genuine. Two tools accept it as an argument; it is not read from the environment and not stored here.

What this server deliberately cannot do

Two steps in setting up an account need a human at a screen, and both stay that way on purpose:

  • Scanning a Telegram QR code.
  • Typing a provider secret.

For each, the agent asks the installation to issue a one-time link, shows it to the person, and polls for the result. The person opens that link in the dashboard, behind their own login, and types the value themselves. Ask an agent to relay a secret through the conversation and it will refuse — that is what the link exists to avoid.

Errors reach the agent intact

The API spends real effort explaining refusals — which ability was missing, which field failed validation, why a send queued nothing. This server passes the body through whole, on success and failure alike, because an agent repairs itself from that text and nothing else.

Licence

MIT. See LICENSE.

Issues and contributions: https://github.com/WardenPoint/wardenpoint-mcp.

Source: README.md at commit 71d1c1b

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.1.2LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts