Skip to main content
Glama
jon-lind-sn

sn-community-events-mcp

by jon-lind-sn
OverviewSchemaSourceRelated ServersDiscussionsAdmin
Python
Remote

sn-community-events-mcp

MCP server that fetches ServiceNow Community events (SNUGs, webinars, World Forum stops, etc. from https://www.servicenow.com/community/events/ct-p/TopLevel_Events) for a date range and returns them as structured data, optionally also writing a CSV.

No login or credentials are required — the underlying API is public.

Example prompts

  • "What ServiceNow community events are happening in the next 30 days?"

  • "Find upcoming virtual webinars about App Engine in Q3 and save them to a CSV."

  • "Give me the full details for the SNUGs in the next two weeks."

Note: Requesting full details individually fetches each matched event's page for its complete description and is drastically slower. When adding "include details" in your prompt try to use smaller date ranges and more narrow queries for faster responses.

Setup

Requires uv installed locally (brew install uv on macOS). uvx fetches and runs the package straight from this repo — no manual cloning or dependency install needed on your end, for either client below. Both re-fetch from main on next launch, so you stay on the latest version automatically.

Claude Code

claude mcp add sn-community-events -- uvx --from git+https://github.com/jon-lind-sn/sn-community-events-mcp sn-community-events-mcp

This registers the server at the user level (available in every project). To scope it to just the current project instead, add --scope project before the --, which writes the entry to .mcp.json in the current directory instead of your global config.

Verify it's registered with claude mcp list, and check connectivity with claude mcp get sn-community-events.

Claude Desktop

  1. Install uv and open the config file:

    macOS

    brew install uv
open -e ~"/Library/Application Support/Claude/claude_desktop_config.json"

    Windows

    winget install --id=astral-sh.uv -e
notepad "$env:APPDATA\Claude\claude_desktop_config.json"

  2. Add the sn-community-events entry below.

    • If the file already has an mcpServers key, add sn-community-events as a new entry inside it, alongside whatever's already there:

      {
  "mcpServers": {
    "sn-community-events": {
      "command": "uvx",
      "args": [
        "--from",
        "git+https://github.com/jon-lind-sn/sn-community-events-mcp",
        "sn-community-events-mcp"
      ]
    }
  }
}

    • If the file is empty paste in the whole block above as-is. If there is no mcpServers key, copy it and its content at the top of the file after the first curly brace.

  3. Restart Claude Desktop for it to pick up the new server.

Related MCP server: snow-mcp

Tool: get_community_events

Argument

Required

Description

start_date

yes

Inclusive start of the date range, YYYY-MM-DD

end_date

yes

Inclusive end of the date range, YYYY-MM-DD

status_category

no

Filter slug. Only upcoming is confirmed to work reliably.

location_category

no

e.g. in-person, virtual, hybrid

product_category

no

e.g. app-engine (slugified UI label)

type_category

no

e.g. webinar, workshop, academy, office-hours

include_full_description

no, default false

Fetch each event's own page for its full description instead of the listing's truncated blurb. One extra HTTP request per matched event — only set true for small date ranges or narrow filters.

save_csv_path

no

If given, also write results to a CSV at this local path.

Returns {"events": [...], "meta": {...}}. meta includes counts worth surfacing to the user (how many events matched, how many full descriptions were/weren't fetched, etc.).

Development notes

To run locally for development:

uv sync
uv run sn-community-events-mcp

Available Tools

1 tool
get_community_eventsA

Fetch ServiceNow Community events (SNUGs, webinars, World Forum stops, etc.) within a date range and return them as structured data.

Args:
    start_date: Inclusive start of the date range, ISO format YYYY-MM-DD.
    end_date: Inclusive end of the date range, ISO format YYYY-MM-DD.
    status_category: Optional filter slug. Only "upcoming" is confirmed to work;
        other values frequently 400 -- if one fails, drop it and retry without it
        rather than guessing an alternate spelling.
    location_category: Optional filter slug, e.g. "in-person", "virtual", "hybrid".
    product_category: Optional filter slug, e.g. "app-engine". The full product
        list is long (from the UI's Product filter) -- pass whatever slug the
        caller gives, or slugify a plain label (lowercase, spaces to hyphens).
    type_category: Optional filter slug, e.g. "webinar", "workshop", "academy",
        "office-hours", "360-exchange".
    include_full_description: If true (default), fetch each matched event's own
        detail page to get the full description instead of the listing's
        "..."-truncated blurb. Costs one extra HTTP request per matched event --
        set to false for date ranges wide enough that this would be slow (a few
        dozen events is quick; a few hundred will take a while, sequentially).
    save_csv_path: If given, also write the results to a CSV file at this path
        (columns: category, title, description, date_text, parsed_date, location,
        url). Embedded line breaks in text fields are rendered as literal `<br>`
        rather than real newlines, so each event stays on one CSV row.

Returns a dict with `events` (list of event dicts) and `meta` (counts: how many
events matched, how many full descriptions were/weren't fetched, etc. -- surface
anything notable from this to the user rather than silently discarding it).
ParametersJSON Schema
NameRequiredDescriptionDefault
end_dateYes
start_dateYes
save_csv_pathNo
type_categoryNo
status_categoryNo
product_categoryNo
location_categoryNo
include_full_descriptionNo

TDQS

A4.8/5.0
Behavior5/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description fully discloses behavior: it fetches detail pages optionally at a cost, writes a CSV when save_csv_path is given, returns specific meta counts, and explains failure modes (status_category 400s). It also notes CSV line-break handling. This far exceeds what annotations would have provided and leaves no safety or side-effect ambiguity.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness5/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is structured cleanly: a one-sentence summary, then a clear Args block with per-parameter explanations. While long, every sentence carries necessary information, especially given 8 parameters and 0% schema coverage. It is front-loaded with the tool's essence and avoids redundancy.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness5/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Owing to the absence of an output schema, the description explicitly details the return structure (events list and meta counts) and the CSV output format. It covers edge cases like truncated descriptions, slow performance, and retry logic. The tool has high complexity, and the description addresses all key aspects, making it complete for an agent.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, yet the description meticulously explains every parameter: date formats, filter slug caveats, examples for type_category, the long product list, performance implications for include_full_description, and CSV column details. It adds enormous meaning beyond the bare schema, exactly what this dimension rewards.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description opens with a specific verb ('Fetch') and a clear resource ('ServiceNow Community events'), enriched with concrete examples (SNUGs, webinars, World Forum stops). It plainly states the tool returns structured data within a date range. Even with no sibling tools to differentiate from, the purpose is unmistakable.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides strong in-tool usage guidance: it explains when to set include_full_description to false for wide date ranges, warns that status_category values other than 'upcoming' may fail, and advises retrying without the filter. It doesn't mention alternative tools (none exist), so the 'when not to use' aspect is absent, but the guidance is clear and actionable.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

  1. 1 tool updatev0.1.0
    • First observedget_community_events
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

TDQS

A4.8/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap. The tool's purpose is clear and singular, so an agent can unambiguously select it for any community events query.

Naming Consistency5/5

The single tool name 'get_community_events' follows a clear verb_noun pattern. There are no other tool names to compare, so consistency is perfect within the server.

Tool Count4/5

A single tool might feel thin, but this server's scope is narrowly defined around fetching ServiceNow community events. The tool itself is feature-rich with many optional filters and output options, so it earns its place.

Completeness5/5

For the stated purpose of retrieving community events, the tool covers all necessary operations: filtering by date, status, location, product, type, and optional full descriptions or CSV export. There are no obvious dead ends or missing capabilities for a read-only events retrieval server.

Maintenance

ActivityMaintained
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

  • snow-mcp

    smitraonline
    A
    license
    A
    quality
    C
    maintenance
    An MCP server for interacting with a ServiceNow instance via its Table API, enabling CRUD operations on incident, request, and requested item tables, as well as generic operations on any table by name.
    22
    MIT

  • sn-community-mcp

    wiz0floyd
    A
    license
    Not graded
    quality
    C
    maintenance
    MCP server for searching the ServiceNow Community forums with relevance-ranked results. Supports fetching posts as Markdown and configurable result counts.
    MIT

  • servicenow-docs

    dasanjaneyuludarla
    F
    license
    Not graded
    quality
    C
    maintenance
    MCP server for searching and reading ServiceNow documentation from a local clone, enabling keyword/regex queries and full doc retrieval without external APIs.
    -