# Pp Exa > Every Exa search API feature, plus local history, spend tracking, and diffing no other Exa tool has. Trigger phrases: `search the web for`, `get the latest news on`, `answer this question with sources`, `find similar pages`, `monitor this topic`, `exa search`, `run exa`. - Skill: `mvanhorn-printing-press-libra/pp-exa` (Agent Skill, multi-file: 280 files) - Install (CLI): `npx skillmds add mvanhorn-printing-press-libra/pp-exa` - Raw SKILL.md: https://api.skillmd.com/api/skills/mvanhorn-printing-press-libra/pp-exa/raw - Safety review: pending - Works with: Claude Code, Claude.ai, OpenAI Codex - Category: Integrations & APIs - License: Apache-2.0 - Author: mvanhorn (https://skillmd.com/u/mvanhorn-printing-press-libra) - Updated: 2026-09-09 - Page: https://skillmd.com/skills/mvanhorn-printing-press-libra/pp-exa --- # Exa — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `exa-pp-cli` binary. **You must verify the CLI is installed before invoking any command from this skill.** If it is missing, install it first: 1. Install via the Printing Press installer. It defaults binaries to `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install exa --cli-only ``` 2. Verify: `exa-pp-cli --version` 3. Ensure the reported install directory is on `$PATH` for the agent/runtime that will invoke this skill. If the `npx` install fails (no Node, offline, etc.), fall back to a direct Go install (requires Go 1.26.6 or newer). This installs into `$GOPATH/bin` (default `$HOME/go/bin`), so add that directory to `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/ai/exa/cmd/exa-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. exa-pp-cli wraps the full Exa API — search, contents, answer, find-similar, monitors, agent runs, websets, webhooks, imports — and adds a local SQLite store so every result, run, and cost lands on disk. Re-run past queries, diff monitor runs, track entity first-seens, and watch spend in real time. ## When to Use This CLI Use exa-pp-cli whenever an agent needs live web research with grounded citations, clean page content, scheduled monitoring, or entity tracking — and wants every search persisted locally for later querying. ## Anti-triggers Do not use this CLI for: - Do not use exa-pp-cli for general web crawling at scale; use a dedicated crawler. - Do not use exa-pp-cli to bypass paywalls or scrape restricted content. - Do not use exa-pp-cli for real-time monitoring dashboards at sub-second cadence; use the API directly. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Local state that compounds - **`spend`** — See cumulative API spend across every Exa call, broken down by day and resource. _Agents should reach for this when they need to know how much Exa usage costs before running another batch._ ```bash exa-pp-cli spend --days 30 --resource searches ``` - **`monitor diff`** — Compare two synced monitor runs and see exactly which URLs are new, gone, or unchanged. _Reach for this to see what a scheduled search found since the last run instead of re-reading entire run outputs._ ```bash exa-pp-cli monitor diff ``` - **`entity report`** — Build a first-seen / last-seen / mention-count timeline for any company or person across your synced searches and webset items. _Reach for this to track when an entity first appeared and how often it shows up across all your research surfaces._ ```bash exa-pp-cli entity report "Acme Corp" --type company --since 30d ``` - **`webset new`** — List items added to a live webset since your last sync, so you only see what changed. _Reach for this for the weekly what's-new sweep over a curated set instead of re-listing every item._ ```bash exa-pp-cli webset new --since 7d ``` ## Command Reference **agent** — Manage agent - `exa-pp-cli agent cancel-run` — Cancel a queued or running Agent run. - `exa-pp-cli agent create-run` — Create an asynchronous Agent run. By default, the API returns the run object immediately. - `exa-pp-cli agent delete-run` — Delete a stored Agent run. - `exa-pp-cli agent get-run` — Retrieve a single Agent run by ID. - `exa-pp-cli agent list-run-events` — List stored events for an Agent run. Set `Accept: text/event-stream` to replay stored events as server-sent events. - `exa-pp-cli agent list-runs` — List Agent runs for your team, ordered from newest to oldest. **answer** — Manage answer - `exa-pp-cli answer` — Performs a search based on the query and generates either a direct answer or a detailed summary with citations **contents** — Manage contents - `exa-pp-cli contents` — Contents **events** — Manage events - `exa-pp-cli events get` — Get a single Event by id. You can subscribe to Events by creating a Webhook. - `exa-pp-cli events list` — List all events that have occurred in the system. You can paginate through the results using the `cursor` parameter. **find-similar** — Manage find similar - `exa-pp-cli find-similar` — Find links similar to the provided URL and optionally retrieve their contents. **imports** — Manage imports - `exa-pp-cli imports create` — Creates a new import to upload your data into Websets. - `exa-pp-cli imports delete` — Deletes a import. - `exa-pp-cli imports get` — Gets a specific import. - `exa-pp-cli imports list` — Lists all imports for the Webset. - `exa-pp-cli imports update` — Updates a import configuration. **monitors** — Manage monitors - `exa-pp-cli monitors batch` — Perform a batch action on monitors matching the provided filters. - `exa-pp-cli monitors create` — Creates a new Monitor to run recurring Exa searches on a schedule. - `exa-pp-cli monitors create-endpoint` — Creates a new `Monitor` to continuously keep your Websets updated with fresh data. - `exa-pp-cli monitors delete` — Deletes a monitor. This cannot be undone. - `exa-pp-cli monitors delete-id` — Deletes a monitor. - `exa-pp-cli monitors get` — Retrieves a single monitor by its ID. - `exa-pp-cli monitors get-id` — Gets a specific monitor. - `exa-pp-cli monitors list` — Lists all monitors for the authenticated team. Supports filtering by status and cursor-based pagination. - `exa-pp-cli monitors list-endpoint` — Lists all monitors for the Webset. - `exa-pp-cli monitors update` — Updates an existing monitor. All fields are optional. - `exa-pp-cli monitors update-id` — Updates a monitor configuration. **teams** — Manage teams - `exa-pp-cli teams` — Returns information about the authenticated team, including current concurrency usage and limits. **webhooks** — Manage webhooks - `exa-pp-cli webhooks create` — Create a Webhook - `exa-pp-cli webhooks delete` — Delete a Webhook - `exa-pp-cli webhooks get` — Get a Webhook - `exa-pp-cli webhooks list` — List webhooks - `exa-pp-cli webhooks update` — Update a Webhook **websearch** — Manage websearch - `exa-pp-cli websearch` — Perform a search with an Exa prompt-engineered query and retrieve a list of relevant results. Optionally get contents. **websets** — Manage websets - `exa-pp-cli websets create` — Creates a new Webset with optional search, import, and enrichment configurations. - `exa-pp-cli websets delete` — Deletes a Webset. Once deleted, the Webset and all its Items will no longer be available. - `exa-pp-cli websets get` — Get a Webset - `exa-pp-cli websets list` — Returns a list of Websets. You can paginate through the results using the `cursor` parameter. - `exa-pp-cli websets preview` — Preview how a search query will be decomposed before creating a webset. - `exa-pp-cli websets update` — Update a Webset ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash exa-pp-cli which "" ``` `which` resolves a natural-language capability query to the best matching command from this CLI's curated feature index. Exit code `0` means at least one match; exit code `2` means no confident match — fall back to `--help` or use a narrower query. ## Recipes ### Deep research with structured output ```bash exa-pp-cli websearch --query "compare the latest frontier AI model releases" --type deep --output-schema '{"type":"object","required":["models"],"properties":{"models":{"type":"array","items":{"type":"object"}}}}' ``` Run deep search and get a synthesized, schema-shaped answer with grounding. ### Monitor a competitor's news ```bash exa-pp-cli monitors create --name "competitor-news" --search-query "new product launches" --search-contents-highlights true ``` Schedule a recurring search, then run `sync` to persist runs locally. ### What changed since last monitor run ```bash exa-pp-cli monitor diff ``` Schedule a recurring search, then run `sync` to persist runs locally. ### Track an entity over time ```bash exa-pp-cli entity report "Acme Corp" --since 30d --agent --select entity,mentionCount ``` Get an agent-shaped first-seen/last-seen timeline for a company across all synced research. ### Narrow a search response with --select ```bash exa-pp-cli websearch --query "AI regulation policy updates" --category news --num-results 5 --select results.title,results.url ``` Request only the high-gravity fields so agent context is not flooded with full result payloads. ## Auth Setup Run `exa-pp-cli auth setup` for the URL and steps to obtain a token (add `--launch` to open the URL). Then store it: ```bash exa-pp-cli auth set-token YOUR_TOKEN_HERE ``` Or set `EXA_API_KEY` as an environment variable. Run `exa-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color --yes`. - **Pipeable** — JSON on stdout, errors on stderr - **Filterable** — `--select` keeps a subset of fields. Dotted paths descend into nested structures; arrays traverse element-wise. Critical for keeping context small on verbose APIs: ```bash exa-pp-cli contents --agent --select id,name,status ``` - **Previewable** — `--dry-run` shows the request without sending - **Offline-friendly** — sync/search commands can use the local SQLite store when available - **Non-interactive** — never prompts, every input is a flag - **Explicit retries** — use `--idempotent` only when an already-existing create should count as success, and use `--ignore-missing` only when a missing delete target should count as success ### Response envelope Commands that read from the local store or the API wrap output in a provenance envelope: ```json { "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."}, "results": } ``` Parse `.results` for data and `.meta.source` to know whether it's live or local. A human-readable `N results (live)` summary is printed to stderr only when stdout is a terminal AND no machine-format flag (`--json`, `--csv`, `--compact`, `--quiet`, `--plain`, `--select`) is set — piped/agent consumers and explicit-format runs get pure JSON on stdout. ## Paths and state Agents should treat the CLI's path resolver as part of the runtime contract: - Use `--home ` for one invocation, or set `EXA_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `EXA_CONFIG_DIR`, `EXA_DATA_DIR`, `EXA_STATE_DIR`, `EXA_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `EXA_HOME`, XDG (`XDG_CONFIG_HOME`, `XDG_DATA_HOME`, `XDG_STATE_HOME`, `XDG_CACHE_HOME`), then platform defaults. - `config` contains settings like `config.toml` and profiles. `data` contains `credentials.toml`, `data.db`, and auth sidecars. `state` contains persisted queries, jobs, and `teach.log`. `cache` contains regenerable HTTP/cache files. - Stored secrets live in `credentials.toml` under the data dir. Existing legacy `config.toml` secrets are read for compatibility and leave `config.toml` on the first auth write. - Run `exa-pp-cli doctor --fail-on warn` to surface path and credential-location warnings. `agent-context` exposes a schema v4 `paths` block for agents that need the resolved dirs. - For MCP, pass relocation through the MCP host config. The MCP binary does not inherit CLI flags: ```json { "mcpServers": { "exa": { "command": "exa-pp-mcp", "env": { "EXA_HOME": "/srv/exa" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `EXA_HOME` or per-kind vars as durable fleet levers, and use `--home` only for a single invocation. Relocation is not reversible by unsetting env vars; move files manually before clearing `EXA_HOME`, or `doctor` will not find credentials left under the former root. ## Automatic learning This CLI ships a self-capturing learning loop. The CLI does its own bookkeeping: every invocation is journaled locally, a failed flag followed by a corrected retry auto-derives a `flag_alias` candidate, and a `teach` on a query family without a playbook auto-synthesizes a `playbook_candidate` from the session's journal. Your job is judgment only: `recall` first, act on surfaced candidates, `teach` the final answer, `playbook amend` when you observe a correction. You never record failures by hand. ### Step 1: `recall` before any discovery Before list/search/drill commands on a new user question, run: ```bash exa-pp-cli recall "" --agent ``` The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "exa-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$ENTITY"], "expected_tool_calls": 3 }, "slots_resolved": { "$ENTITY": { "token": "", "canonical": "" } }, "notes": "" }, "notes": "" } ``` Empty-store short-circuit: if the store has no learnings, playbooks, or candidates yet (recall finds nothing and `learnings list` and `learnings candidates` are both empty), skip recall for the rest of this session instead of taxing every query; resume recall-first once something has been taught. ### Step 2: decision tree Read `candidates`, `playbook`, `notes`, `results[0]`, and warnings in that order: ``` if Candidates present (warnings include "candidates_present"): -> candidates are try-then-confirm, never facts. Follow each candidate's two-step next_action verbatim: run the trial command first, then run `learnings confirm ` only after the trial verified the behavior. Reject a wrong candidate with `learnings reject `. -> NEVER re-teach something recall surfaced as a candidate; confirm or reject that candidate instead of teaching a duplicate. -> candidates ride alongside playbooks and resource hits, not instead of them; continue with the branches below after acting on them. if Playbook present: -> READ Playbook.notes verbatim FIRST (workarounds + gotchas the CLI surface doesn't expose) -> replay Playbook.steps in order, substituting Playbook.slots_resolved entries for the entity slot tokens. If a step's slot is unresolved, fall back to discovery for that step only. -> the Playbook's expected_tool_calls is a budget; if you find yourself running materially more, record the divergence via `exa-pp-cli playbook amend` at end-of-session. elif Notes present (no Playbook): -> read Notes verbatim before any discovery step; they carry known gotchas for this query family even when no structured choreography exists yet. elif Found AND Results[0].EntityMatch == "exact" AND Results[0].Confidence >= 2: -> skip discovery; fetch live data for Results[*].ResourceID in parallel elif Found AND Results[0].EntityMatch == "partial": -> candidate hint, NOT a hit; read the resource title to validate before trusting elif (any row in Mismatches[] when --debug-mismatches was passed): -> treat as cold start; the stored learning is for a different entity (different canonical resolved from query_entities) else: // Found == false, no playbook, no notes -> cold start; run discovery normally; teach the answer afterward (Step 4). If the family has no playbook yet, that teach auto-synthesizes a playbook candidate from this session's journal - you do not need to record one by hand. ``` Playbook and Notes are orthogonal to the per-resource path. A recall response can carry both a Playbook AND a `Results[]` hit - use both: the Playbook tells you which choreography to run; the resource hits short-circuit specific steps. Default to skipping `mismatches`; pass `--debug-mismatches` only when investigating cold-start surprises. Candidate judgment details: `learnings confirm ` prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. `learnings reject ` tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; `exa-pp-cli learnings candidates` lists the full open set. Graceful degradation: if `learnings confirm` is an unknown command, you are driving an older binary - ignore the candidates guidance and follow the rest of the protocol. ### Step 3: always read `warnings` - `low_confidence`: row exists at `confidence<2`. Treat as a hint, not a skip-discovery hit. - `resource_not_in_store`: the local store doesn't have the resource the learning points at. The match validator couldn't classify entities — direct-fetch and re-evaluate. - `cross_alias_match` (per-result): the row was taught under a different alias and matched the live query's canonical via `entity_lookups` (e.g., a "USA" teach satisfying a "United States" recall). Trust the resource_id. - `similar_shape_different_entity:` (top-level): a structurally matching row exists but its canonical entity differs from the live query's. Treated as cold start; the warning carries the conflicting canonical as a hint, but the row is NOT promoted into Results. - `ambiguous_alias` (top-level): a single query entity resolved to multiple canonicals (e.g., "Cards" → Arizona Cardinals + St. Louis Cardinals). Surface the ambiguity from context before committing to a resource. - `candidates_present` (top-level): the envelope carries a `candidates` section. Handle it via the candidates branch in Step 2 before anything else. - `lookup_refresh_available` (top-level): an entity in the query has no lookup row yet, but synced data could provide one. Run `exa-pp-cli sync` to refresh entity lookups. - Top-level `no_learnings_for_query_family`: the table had no rows above the Jaccard floor. Pure cold start. ### Step 4: `teach &` after finalizing your response - always Teaching is unconditional. After resolving a query the store could not answer, background-teach the final resource mapping - no call-count threshold, no judging whether it was "worth" learning. The teach is the anchor of the loop: it triggers playbook synthesis for a family without a playbook, and same-referent phrasings fold into one family so near-duplicate teaches do not fragment the store. Fire it after assembling your user-facing response but BEFORE emitting it, with a shell `&` so the call returns immediately: ```bash exa-pp-cli teach --query "" --resource-type --resource --resource # (append shell `&` to background it) ``` Silent on success. Errors only land in `teach.log` under the resolved state dir. Teach the **most specific** resource - if the user asked a broad question and you walked through parent records to find the specific answer, teach the leaf id, not the parent. The CLI uses seeded `entity_lookups` for cross-alias resolution at recall time, so a teach under one alias (e.g., "Niners") satisfies future queries under another alias (e.g., "49ers", "San Francisco") automatically. PII rule: teach the structural question with identifiers stripped - never include names, emails, phone numbers, account ids, or other personal identifiers in taught queries or notes. The CLI scans teach queries for obvious email/phone shapes and warns, but does not block; strip before teaching rather than relying on the warning. ### Step 5: playbooks - optional flags, automatic synthesis You do not need to decide whether a session "deserves" a playbook: a teach on a family without one auto-synthesizes a `playbook_candidate` from the session's journal, and the next session judges it via confirm/reject. Attach explicit playbook flags only when you already hold choreography worth recording verbatim - workarounds the CLI didn't surface (silently-dropped flags, undocumented params, pagination tricks, payload gotchas). Prefer the **integrated one-call form** - record the resource learning and the playbook in the same `teach` invocation: ```bash # Common case: record both the resource learning AND the playbook in one call. exa-pp-cli teach \ --query "" \ --resource \ --playbook-file ~/playbooks/.json \ --playbook-notes-file ~/playbooks/-notes.md # (append shell `&` to background it) # Alternate: playbook-only (no resource to record alongside). exa-pp-cli teach-playbook \ --query "" \ --playbook-file ~/playbooks/.json \ --notes-file ~/playbooks/-notes.md ``` Playbook files are JSON with `steps`, `entity_slots`, `expected_tool_calls`. Notes files are markdown carrying the gotchas verbatim. File-free callers (MCP-only agents) pass the same content inline: `--playbook-json` and `--playbook-notes` on the integrated `teach` form, `--playbook-json` and `--notes` on `teach-playbook`. On the integrated `teach` form, the playbook flags are optional - omit them entirely for a resource-only teach. On the standalone `teach-playbook` form, at least one of the playbook and notes flags must be set; both empty is rejected. Playbooks are keyed on the structural query family (entities stripped) so a recipe taught from one entity-shaped query applies to every other query of the same shape, with `slots_resolved` binding the live query's canonical at recall time. When you DO find a playbook on a future recall, treat it as ground truth: replay the steps with `slots_resolved` substitutions, skip the discovery that the choreography already documents, and read `notes` before any step. ### Step 6: `playbook amend &` when your debug response identifies a correction If your debug-protocol response identifies a concrete correction the notes or playbook should know — a workaround, an undocumented endpoint shape, a stale field name, observed schema drift, an empty-payload fallback — fire `playbook amend` BEFORE emitting your user-facing response. Same fire-and-forget posture as `teach`. ```bash exa-pp-cli playbook amend \ --query "" \ --add-note "" # (append shell `&` to background it) ``` What counts as worth amending: a behavior you OBSERVED this session that future-you would benefit from knowing. Examples worth amending: - A workaround for a CLI surface that silently drops or misorders a flag. - An undocumented endpoint shape (response wrapped in `{meta, results}`, payload nested two levels deeper than the docs claim). - Observed schema drift (a field renamed, an index that shifted between seasons, a category label that the API now returns lower-cased). What does NOT belong in notes: - The year-specific or entity-specific answer to the user's question. That's the response, not a learning. - Per-team / per-athlete / per-row data the playbook already retrieves at runtime. - Statements that paraphrase what the existing notes already say. The amend command appends to the family's existing notes with a timestamped marker (`[amend YYYY-MM-DDTHH:MMZ]: `). Multiple amends accumulate; the audit trail is visible. If no playbook exists yet for the family, amend creates a notes-only one (so cold-start corrections still land). #### PII discipline for amend notes `playbook amend` notes are designed to potentially flow upstream as shared knowledge in future versions of the Printing Press. Keep them clean of user-identifying content so the upstream-contribution path stays open without retroactive scrubbing: - **Do NOT embed** paths to user filesystems, personal API keys or tokens, user email addresses, user GitHub handles, or specific query histories tied to a single user. - **Acceptable**: endpoint shapes, undocumented field names, API gotchas, observed schema drift, workarounds for CLI surfaces, generalizable pagination or retry tactics. If a correction is only meaningful with user-specific context, it belongs in a personal note, not in the playbook amend. ### Measuring the loop `exa-pp-cli learnings stats` reports recall hit rate, teach-to-reuse, playbook resolution rate, and candidate confirm/reject counts from the local `learn_events` table. Rates are null until they have a denominator; everything stays on this machine. Use it to check whether the loop is earning its keep for this CLI. ### Disabling learning - `--no-learn` on a single command short-circuits both `recall` and the `teach` write path. Use for deterministic agent flows or tests that must not be affected by accumulated learnings. - `EXA_NO_LEARN=true` in the environment globally disables the pipeline. ## Agent Feedback When you (or the agent) notice something off about this CLI, record it: ``` exa-pp-cli feedback "the --since flag is inclusive but docs say exclusive" exa-pp-cli feedback --stdin < notes.txt exa-pp-cli feedback list --json --limit 10 ``` Entries are stored locally as `feedback.jsonl` under the resolved data dir. They are never POSTed unless `EXA_FEEDBACK_ENDPOINT` is set AND either `--send` is passed or `EXA_FEEDBACK_AUTO_SEND=true`. Default behavior is local-only. Write what *surprised* you, not a bug report. Short, specific, one line: that is the part that compounds. ## Output Delivery Every command accepts `--deliver `. The output goes to the named sink in addition to (or instead of) stdout, so agents can route command results without hand-piping. Three sinks are supported: | Sink | Effect | |------|--------| | `stdout` | Default; write to stdout only | | `file:` | Atomically write output to `` (tmp + rename) | | `webhook:` | POST the output body to the URL (`application/json` or `application/x-ndjson` when `--compact`) | Unknown schemes are refused with a structured error naming the supported set. Webhook failures return non-zero and log the URL + HTTP status on stderr. ## Named Profiles A profile is a saved set of flag values, reused across invocations. Use it when a scheduled or recurring agent reuses the same saved flags while providing different input each run. ``` exa-pp-cli profile save briefing --json exa-pp-cli --profile briefing contents exa-pp-cli profile list --json exa-pp-cli profile show briefing exa-pp-cli profile delete briefing --yes ``` Explicit flags always win over profile values; profile values win over defaults. `agent-context` lists all available profiles under `available_profiles` so introspecting agents discover them at runtime. ## Exit Codes | Code | Meaning | |------|---------| | 0 | Success | | 2 | Usage error (wrong arguments) | | 3 | Resource not found | | 4 | Authentication required | | 5 | API error (upstream issue) | | 7 | Rate limited (wait and retry) | | 10 | Config error | ## Argument Parsing Parse `$ARGUMENTS`: 1. **Empty, `help`, or `--help`** → show `exa-pp-cli --help` output 2. **Starts with `install`** → ends with `mcp` → MCP installation; otherwise → see Prerequisites above 3. **Anything else** → Direct Use (execute as CLI command with `--agent`) ## MCP Server Installation 1. Install the MCP server: ```bash go install github.com/mvanhorn/printing-press-library/library/ai/exa/cmd/exa-pp-mcp@latest ``` 2. Register with Claude Code: ```bash claude mcp add exa-pp-mcp -- exa-pp-mcp ``` 3. Verify: `claude mcp list` ## Direct Use 1. Check if installed: `which exa-pp-cli` If not found, offer to install (see Prerequisites at the top of this skill). 2. Match the user query to the best command from the Unique Capabilities and Command Reference above. 3. Execute with the `--agent` flag: ```bash exa-pp-cli [subcommand] [args] --agent ``` 4. If ambiguous, drill into subcommand help: `exa-pp-cli --help`.