Pp Serply

Serply — Printing Press CLI

Prerequisites: Install the CLI

This skill drives the serply-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:

   npx -y @mvanhorn/printing-press-library install serply --cli-only

2. Verify: serply-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:

go install github.com/mvanhorn/printing-press-library/library/ai/serply/cmd/serply-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.

Nine Serply search verticals as typed commands and MCP tools, with per-country proxies and device emulation on each. On top, rank finds a domain's position for a query, serp diff reports what moved since the last run, and research merges web, news and scholar results into one cited brief.

When to Use This CLI

Use this CLI when an agent or script needs live search engine results: Google web, News, Scholar, Images, Video, Jobs, Shopping, Maps, or Bing. It fits grounding answers in current sources, checking where a site ranks from a given country, and watching a results page for changes over time.

Anti-triggers

Do not use this CLI for:

• Do not use it to read the full text of a page; it returns result titles, links and snippets.
• Do not use it for semantic or embedding search over your own documents.
• Do not loop it over hundreds of queries without checking credit cost first; every uncached call is billed.

Unique Capabilities

These capabilities aren't available in any other tool for this API.

SEO checks

• rank — See the position of a domain for a query, optionally from a specific country, in one call.

  Reach for this instead of a raw web search when the task is where a site ranks, not what the results are.

  serply-pp-cli rank github.com --q "open source cli" --x-proxy-location US --agent

• serp diff — See which URLs entered, left, or moved in a results page since the last time you ran the same query.

  Use it for recurring monitoring of a query; the first run stores a baseline and later runs report only what changed.

  serply-pp-cli serp diff --q "best static site generator" --agent

Agent research

• research — Get one deduplicated, numbered source list for a topic from web, news and scholar results at once.

  Reach for this when an answer needs sources of more than one kind, such as current coverage plus papers.

  serply-pp-cli research "retrieval augmented generation evaluation" --num 5 --agent

Command Reference

bing — Manage bing

• serply-pp-cli bing — Search Bing and return organic results.

images — Manage images

• serply-pp-cli images — Search Google Images.

job_search — Manage job search

• serply-pp-cli job-search — Search job listings indexed by Google Jobs.

maps — Manage maps

• serply-pp-cli maps <query> — Search Google Maps for places. The query is a path segment.

news — Manage news

• serply-pp-cli news — Search Google News and return recent articles.

products — Manage products

• serply-pp-cli products — Search Amazon products with price, rating and review count.

scholar — Manage scholar

• serply-pp-cli scholar — Search Google Scholar for papers, authors and citations.

videos — Manage videos

• serply-pp-cli videos — Search Google Videos.

web — Manage web

• serply-pp-cli web — Search Google and return organic results with title, link and description.

Finding the right command

When you know what you want to do but not which command does it, ask the CLI directly:

serply-pp-cli which "<capability in your own words>"

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. --json (and other machine formats) keep that exit-2 contract and write {"matches":[]} on stdout so agents can inspect the envelope without treating a miss as success.

Recipes

Narrow a web search to links

serply-pp-cli web --q "site:serply.io docs" --num 5 --agent --select results.title,results.link

Keeps agent context small by returning only titles and links.

Rank from another country

serply-pp-cli rank serply.io --q "serp api" --x-proxy-location GB

Runs the search through a UK proxy and reports the first matching position.

Watch a results page

serply-pp-cli serp diff --q "best static site generator"

First run stores a baseline; later runs list entered, left and moved URLs.

Papers plus coverage

serply-pp-cli research "small language models" --num 5

One brief with numbered sources from web, news and scholar.

Auth Setup

Run serply-pp-cli auth setup to print the URL and steps for getting a key (add --launch to open the URL). Then set:

export SERPLY_API_KEY="<your-key>"

To persist credentials, use echo "$TOKEN" | serply-pp-cli auth set-token. Stored secrets live in credentials.toml under the data dir, not in config.toml.

Run serply-pp-cli doctor to verify setup.

Agent Mode

Add --agent to any command. Expands to: --json --compact --no-input --no-color.

Global format flags share one contract on promoted, novel, sync, and --deliver paths:

• --json — one JSON document on stdout (sync progress events go to stderr)

• --compact — keep identity/status/timestamp fields; does not change the document vs stream shape

• --csv / --plain — tabular rows (collection envelopes unwrap to the row array)

• --quiet — one identity value per row, no envelope

• 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:

  serply-pp-cli bing --q "model context protocol" --agent --select description,link,realPosition

• 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

• Read-only — do not use this CLI for create, update, delete, publish, comment, upvote, invite, order, send, or other mutating requests

Response envelope

Commands that read from the local store or the API wrap output in a provenance envelope:

{
  "meta": {"source": "live" | "local", "synced_at": "...", "reason": "..."},
  "results": <data>
}

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 <dir> for one invocation, or set SERPLY_HOME=<dir> to relocate all four path kinds under one root.

• Use per-kind env vars only when a specific kind must diverge: SERPLY_CONFIG_DIR, SERPLY_DATA_DIR, SERPLY_STATE_DIR, SERPLY_CACHE_DIR.

• Resolution order is per-kind env var, --home, SERPLY_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, cookies, 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 serply-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:

  {
    "mcpServers": {
      "serply": {
        "command": "serply-pp-mcp",
        "env": {
          "SERPLY_HOME": "/srv/serply"
        }
      }
    }
  }

Fleet precedence: an inherited per-kind env var overrides an explicit --home for that kind. Use SERPLY_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 SERPLY_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, pass the question as an argv or MCP tool argument to recall --agent. Do not interpolate user-controlled text into a shell command line.

Quoted recall "<question>" breaks on an apostrophe, which is ordinary English. A quoted heredoc breaks when a body line equals the delimiter, and that delimiter is published in these docs. Write the question with a non-shell file-writing tool, then read it back as data:

# Write the question verbatim with your file-writing tool (no shell involved).
# Command substitution on a file only ever yields data — the shell never
# parses the file's bytes as syntax.
QUERY=$(cat /path/to/question.txt)
serply-pp-cli recall "$QUERY" --agent

Prefer MCP: pass the question as the tool's query argument. "$QUERY" after a file read is argv-safe; putting the question itself in the command text is not.

The response envelope:

{
  "query": "...",
  "normalized": "<normalized form>",
  "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": ["<trial command>", "serply-pp-cli learnings confirm 12"] }
  ],
  "playbook": {
    "query_family": "...",
    "playbook": {
      "steps": [ { "cmd": "<command with {slot} substitution>", "purpose": "..." } ],
      "entity_slots": ["$ENTITY"],
      "expected_tool_calls": 3
    },
    "slots_resolved": { "$ENTITY": { "token": "<live token>", "canonical": "<canonical>" } },
    "notes": "<workarounds + gotchas for this query family>"
  },
  "notes": "<duplicate surface for non-playbook callers>"
}

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 <id>` only after the trial verified the behavior.
       Reject a wrong candidate with `learnings reject <id>`.
    -> 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 `serply-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 <id> prints the candidate's full payload before materializing it - check that the printed payload matches the behavior you verified. learnings reject <id> tombstones the derivation signature so the same candidate does not resurface. The envelope carries only the few candidates worth acting on now; serply-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:<canonical> (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 serply-pp-cli sync --resources images,news,scholar,videos to refresh entity lookups.
• Top-level no_learnings_for_query_family: the table had no rows above the Jaccard floor. Pure cold start.