Skip to main content
Glama
atrisorb
by atrisorb

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
FLOWRELAY_API_KEYYesYour Flow Relay API key
FLOWRELAY_BASE_URLNoOptional base URL for the Flow Relay API
FLOWRELAY_PROJECT_IDNoOptional default project ID to set project context

Capabilities

Features and capabilities supported by this server

CapabilityDetails
tools
{
  "listChanged": true
}

Tools

Functions exposed to the LLM to take actions

NameDescription
get_workspace_contextA

Show the current Flow Relay context: personal vs business mode, number of organizations and accessible projects, the active project scope and the caller's role. Good first call to orient yourself before other tools.

list_projectsA

List every project the API key can access (personal and organization), each with its id, scope and the caller's role. The id returned here is what you pass as project_id to the generate_* and list tools – start here whenever you need one.

set_active_projectA

Set the active project so later tools can omit project_id (a convenience for a multi-step session on one project). Set it once from a list_projects id, then call generate_handoff / list_events / etc. without repeating project_id. Not required if you always pass project_id explicitly.

list_handoffsA

List existing handoffs (newest first) with their full content, across all accessible projects or one project. Use this to read what has already been generated before spending credits on a new generate_handoff. Each row's id can be sent to Discord via discord_send_message.

generate_handoffA

Generate a project handoff: an AI summary of recent activity, key changes, decisions, open questions and next steps for a project. Runs synchronously – waits for completion (tens of seconds) and returns the finished Markdown. Requires an active project (set_active_project) or an explicit project_id from list_projects. Consumes credits from the user's plan, charged once on success – prefer list_handoffs to read an existing one before generating a new one. To scope it, pass sources and/or filters (call list_filter_options first for valid values); omit both to use the project's saved scope preferences.

list_integrationsA

List connected integrations. With a project scope it returns the resources bound to that project plus their health (connection status, provider coverage); without one it returns the sources the API key owner has connected. Use it to check what data a generation can draw on.

list_untracked_resourcesA

List active resources (repos, channels, boards) that produced events recently but are not yet assigned to any project. Use it to spot data the user connected but has not organized into a project yet – mapping them (in the web dashboard) makes their events available to generations.

list_eventsA

List recent raw context events (individual pieces of tracked activity: a push, a message, an issue update) newest first. Use it to inspect the underlying signal a generation would draw on, or to check whether a source is producing data. With a project scope it is limited to that project's bound resources.

discord_list_channelsA

List the text channels in the Discord server connected to this account, each with its id. Call this to get a channel_id before discord_send_message.

discord_send_messageA

Send to a Discord channel in your connected server. Provide exactly one of: content (inline text); handoff_id or insight_id (sends that artifact, rendered to Markdown, as a .md file attachment); or artifact (last_handoff / last_correlation / last_onboarding / last_architecture / last_release_notes, with project_id) to send the latest active artifact of that kind.

generate_correlation_insightA

Generate a cross-source correlation insight: finds related events across different sources (e.g. a Slack thread, a Jira ticket and the PR that resolved it) and surfaces the links, patterns and open threads. Use when the user wants to understand how activity connects across tools. Runs synchronously and returns Markdown. Consumes credits, charged once on success. Call list_filter_options before using filters.

generate_onboarding_briefA

Generate an onboarding brief: a getting-started guide for someone new to the project – key people, key decisions, pitfalls and recommended reading drawn from recent activity. Use when a new team member needs to get up to speed. Runs synchronously and returns Markdown. Consumes credits, charged once on success. Call list_filter_options before using filters.

generate_architecture_insightA

Generate an architecture insight: trade-offs, risks, patterns and recommendations inferred from the project's code activity (requires a connected code source – github, gitlab, bitbucket or azure_devops). This is the deepest and most expensive insight (it runs extended reasoning). Use for technical review of architectural direction. Runs synchronously and returns Markdown. Consumes credits, charged once on success. Call list_filter_options before using filters.

generate_release_notesA

Generate release notes or a PR description from recent code activity (commits, PRs, builds). Runs synchronously and returns Markdown. Consumes 3 credits on success.

list_digestsB

List past scheduled activity digests for a project.

list_insightsA

List existing insights for a project (newest first) with their content. Use this to read what has already been generated before spending credits on a new generate_*_insight. Each row's id can be sent to Discord via discord_send_message.

ask_projectA

Ask one question about a project and get an answer grounded in its indexed codebase, connected baselines and last 14 days of activity. Answers synchronously – there is no job to poll. Costs 2 credits per question, so prefer list_handoffs / list_insights when an existing artifact already answers it.

list_filter_optionsA

List the real per-source filter values (resources, branches, event types, priorities) available for a project. Call this BEFORE generate_handoff or any generate_*_insight so the "filters" argument uses real values instead of guesses. Pass a resource id into filters[source].projects, a branch name into .branches, an event type into .eventTypes, a priority into .priorities.

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription

No resources

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/atrisorb/flowrelay-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server