PandaDoc MCP

Bucket every document by how long it has sat in its current status — where the pipeline piles up. Use this command to bucket ALL documents by time-in-current-status. Do NOT use it to find only sent-but-unsigned deals past a threshold; use 'stalled' instead. Reads the local store — run `sync` first. Needs date_modified across all docs joined to status, which no single API call returns.

Analyze locally synced data with count, group-by, and summary operations. Data must be synced first with the sync command.

Rank clients (recipient emails) by how long since they last signed any document, surfacing accounts that have gone quiet. Use this command to rank CLIENTS/contacts by recency — how long since they last signed anything. Do NOT use it to rank recipients by completion rate; use 'engagement' instead. Reads the local store — run `sync` first. Joins each document's embedded recipients against completion dates across the whole corpus; requires recipient data to be present in synced documents.

Get API domain context: resource taxonomy, auth requirements, query tips, and unique capabilities. Call this first.

Rank recipients by how often the documents they are on reach completion. A recipient on many documents with few completions is a chronic staller. Use this command to rank RECIPIENTS by completion RATE across documents. Do NOT use it to rank clients by how long since they last signed; use 'cold-clients' instead. Reads the local store — run `sync` first. Joins each document's embedded recipients with the document's status, a recipient-centric rollup the PandaDoc API cannot return in one call. Requires recipient data to be present in synced documents.

Export paginated API data to a local file. Supports JSONL (one JSON object per line, streaming-friendly) and JSON (array). JSONL is recommended for large datasets as it has no memory pressure.

Produce an actionable nudge worklist: open documents idle for N+ days, joined to their recipient emails, ordered coldest-and-biggest first. Use this command to produce an actionable NUDGE worklist: stalled documents joined to recipient emails + days-sent, ordered for outreach. Do NOT use it for the raw stalled-document list with no contact join; use 'stalled' instead. Reads the local store — run `sync` first. Recipient emails require recipient data to be present in synced documents; items without it still list with an empty recipients array.

Bucket the open (non-terminal) document pipeline's quote dollars into healthy, aging, and stalled tiers by days since last activity. Use this command to bucket open quote DOLLARS by deal age/risk. Do NOT use it for a single flat open-value total; use 'value' instead. Do NOT use it to list the stalled documents themselves; use 'stalled'. Reads the local store — run `sync` first. Tier boundaries default to <7 days healthy and 7-14 days aging; tune with --healthy-days/--aging-days.

Import data from a JSONL file by issuing POST requests for each record. Each line must be a valid JSON object. Failed records are logged to stderr but do not stop the import.

Execute one pandadoc API endpoint by its endpoint_id (from pandadoc_search). Params are passed as a JSON object; path placeholders and query strings are resolved automatically.

Search the pandadoc API for endpoints matching a natural-language query. Returns a ranked list of {endpoint_id, method, path, summary} entries. Call this first to find the endpoint to execute.

Show the whole document funnel at a glance: how many documents sit in each status across every synced document, plus a view-to-sign rate. Reads the local store — run `sync` first. The PandaDoc API returns one page of documents at a time with no status rollup; this aggregates the full corpus locally.

Find open (sent/viewed) documents whose auto-reminders are disabled — the deals where PandaDoc is not nudging the signer for you. Use this command to find open documents missing an automated REMINDER. Do NOT use it to find documents past a staleness threshold regardless of reminders; use 'stalled' instead. Selects open documents from the local store (run `sync` first), then calls the live auto-reminders endpoint per document — it requires API credentials and respects --max-scan-docs to bound the fan-out.

Full-text search across all synced data. Faster than paginating list endpoints. Requires sync first.

Show what changed in the last window: documents created and documents modified within the lookback (default 24h). Accepts windows like 4h, 90m, 2d, 1w. Reads the local store — run `sync` first. A time-windowed change view across the whole corpus.

Run read-only SQL against local database. Use for ad-hoc analysis, aggregations, and joins across synced resources. Requires sync first.

Find documents that were sent but never completed within N days — the deals quietly dying. Use this command for documents SENT and never completed within N days. Do NOT use it for time-in-current-status bucketing; use 'aging' instead. Do NOT use it when you need recipient emails attached for outreach; use 'followup' instead. Reads the local store — run `sync` first.

Sync data from the API into a local SQLite database. Supports resumable incremental sync (only fetches new data since last sync) and full resync. Once synced, use the 'search' command for instant full-text search. Exit codes & warnings: Resources the API denies access to (HTTP 403, or HTTP 400 with an access-policy body) are reported as warnings rather than failing the run. In --json mode each is emitted as a {"event":"sync_warning",...} line carrying status, reason, and message fields, and a final {"event":"sync_summary",...} aggregates the run. Exit 0 when at least one resource synced and no resource flagged in the spec as critical (x-critical: true) failed; non-critical failures emit {"event":"sync_warning","reason":"exit_policy_default_changed", ...} so callers can detect that a partial failure was tolerated. Pass --strict to exit non-zero on any per-resource failure. Exit is always non-zero when every selected resource failed, regardless of --strict. Resource scoping: --resources runs the named top-level resources, plus any parent-keyed dependent whose own name is listed OR whose parent table is listed. Naming a parent therefore cascades to its dependents (so "sync this parent and its children" works without listing every nested resource by hand). There is no flag today to suppress the cascade for a named parent. To run a dependent without re-syncing its parent, list only the dependent by name; the parent table must already be populated from a prior sync.

Tail streams live data changes by polling the API at configurable intervals. Events are emitted as NDJSON to stdout for piping to other tools. Gracefully shuts down on SIGTERM/SIGINT. Note: For APIs with WebSocket or SSE support, a future version will use native streaming instead of polling.

Rank templates by how they perform: documents generated, completed, declined, still open, and a completion rate. Surfaces which templates actually close. Reads the local store — run `sync` first. Joins documents back to their templates and aggregates terminal status, which the PandaDoc API has no endpoint for.

Sum open quote/pricing value across all in-flight documents, grouped by status or template. Use this command for a flat open-value TOTAL by status. Do NOT use it to bucket dollars by deal age/risk; use 'forecast' instead. Reads the local store — run `sync` first. No API endpoint aggregates value across documents.

Compare the event types your webhook subscriptions listen for against the documented PandaDoc event catalog. Surfaces events nobody is subscribed to and counts inactive subscriptions. Reads the local store — run `sync` first. Joins subscribed triggers against the known catalog, a coverage view the PandaDoc API never reports as a gap list.

Compound workflows that combine multiple API operations

Archive fetches all syncable resources from the API and stores them in a local SQLite database. Supports incremental sync (only new data since last run) and full resync. After archiving, use 'search' for instant full-text search.

Show local archive status and sync state for all resources