papi-integration-recipe

Integration Recipe — PAPI as system of record

Your AI session is the integration bus. Any MCP tool you have connected — Sentry, Linear, GitHub, Slack — can push data into PAPI without additional infrastructure.

1. Read from connected tool  →  2. Map to PAPI shape  →  3. Write via PAPI tool

PAPI handles auth for PAPI. The other tool handles its own auth. The agent session passes data between them. No token vaults, no sync workers, no egress.

---

Recipe: Sentry error → PAPI idea

Trigger: Production error needs a backlog task before context is lost.

# Step 1 — Read from Sentry
mcp__sentry__list_issues(project="your-project", status="unresolved", limit=5)

# Step 2 — Pick an issue, extract: title, fingerprint, URL

# Step 3 — Write to PAPI
mcp__papi__idea(
  text="Fix: <error title>",
  notes="Production error. Fingerprint: <id>.\nReference: <sentry-issue-url>",
  priority="P1 High",
  module="core"
)

---

Recipe: Linear issue → PAPI board_edit

Trigger: Sync Linear issue state into an existing PAPI task.

# Step 1 — Read from Linear
mcp__linear__get_issue(id="LIN-123")

# Step 2 — Resolve LIN-123 to PAPI task_id (by notes lookup or title match)

# Step 3 — Update PAPI task
mcp__papi__board_edit(
  task_id="task-NNN",
  notes="Linear LIN-123 — <status>. <description>."
)

---

Recipe: GitHub issue → PAPI idea

Trigger: New bug filed on GitHub → triage into PAPI backlog.

# Step 1 — Read from GitHub
mcp__github__list_issues(repo="org/repo", state="open", labels=["bug"])

# Step 2 — For each issue: extract number, title, URL

# Step 3 — Write to PAPI
mcp__papi__idea(
  text="GH#<number>: <issue title>",
  notes="Filed on GitHub.\nReference: <issue-url>",
  priority="P2 Medium"
)

---

Pattern template — works for any source

Step	What to do
Read	mcp__<tool>__<read_fn>(params)
Map	Extract: title, reference URL, priority from source
Write	mcp__papi__idea(text, notes) for new items; mcp__papi__board_edit(task_id, ...) for updates