campaign-preflight-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
No arguments | |||
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
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| preflight_demoA | READ-ONLY. Run the bundled synthetic demo campaign and return its readiness report. Uses synthetic data shipped with the package: no network calls and no credentials. Useful for showing what a report looks like. |
| preflight_filesA | READ-ONLY. Check a campaign described by local files and return its readiness report. Reads only the paths given here; no directory is scanned or walked. Optional inputs that are omitted are reported as unavailable capabilities, so a run without suppressions_path says the suppression checks did not run rather than implying the list is clean. |
| preflight_instantly_campaignA | READ-ONLY. Inspect a live Instantly campaign and return its readiness report. Reads the campaign, its leads, its sending accounts, and the workspace block list. Every request is checked against a read-only allowlist before it leaves the process, so no write, activation, or lead-mutation call is reachable. The API key is read from the INSTANTLY_API_KEY environment variable and is never accepted as a tool argument. |
| list_preflight_rulesA | READ-ONLY. List the preflight rule catalogue, optionally filtered by category: campaign, contacts, suppression, personalization, copy, schedule, or senders. |
| explain_preflight_ruleB | READ-ONLY. Explain one rule: what it checks, what data it needs, and its configurable options. |
| validate_preflight_configA | READ-ONLY. Validate a rules configuration file without running any checks. Reports unknown rule ids, unknown options, and out-of-range values. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 6 tools
Each tool serves a clearly distinct purpose: three preflight runners for different input sources (demo, files, live), two for rule management (list and explain), and one for config validation. There is no overlap in their operations, and the descriptions make it obvious which to select.
Names use a consistent 'preflight_' prefix across all tools, but the pattern is not fully uniform: the first three are verbs implied by the domain (e.g., 'preflight_demo' runs a demo), while the last three explicitly start with verbs ('list_', 'explain_', 'validate_'). This is a minor deviation that agents can easily adapt to.
With six tools, the server is well-scoped and avoids unnecessary bloat. Each tool covers a distinct aspect of the preflight workflow—execution sources, rule catalog, and configuration—so the count feels appropriately sized for the domain.
The surface covers the core lifecycle: running preflights on demo, files, or a live Instantly campaign; inspecting and understanding rules; and validating config files. A minor gap is the lack of a tool to run preflight on a manually specified set of parameters or a generic input, but the provided sources handle common use cases adequately.