--- name: pp-mcpmarket description: "Every MCP Market search, leaderboard, and skill lookup — plus trending deltas, sync diffs, and author portfolios no other tool tracks. Trigger phrases: `find an MCP server for X`, `search mcp market`, `what's trending on mcp market`, `check mcpmarket for a skill`, `use mcpmarket`, `run mcpmarket`." author: "Som Samantray" license: "Apache-2.0" argument-hint: " [args] | install cli|mcp" allowed-tools: "Read Bash" metadata: openclaw: requires: bins: - mcpmarket-pp-cli install: - kind: go bins: [mcpmarket-pp-cli] module: github.com/mvanhorn/printing-press-library/library/developer-tools/mcpmarket/cmd/mcpmarket-pp-cli --- # MCP Market — Printing Press CLI ## Prerequisites: Install the CLI This skill drives the `mcpmarket-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 `$HOME/.local/bin` on macOS/Linux and `%LOCALAPPDATA%\Programs\PrintingPress\bin` on Windows: ```bash npx -y @mvanhorn/printing-press-library install mcpmarket --cli-only ``` 2. Verify: `mcpmarket-pp-cli --version` 3. Ensure the reported install directory is on `$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 `$PATH` instead: ```bash go install github.com/mvanhorn/printing-press-library/library/developer-tools/mcpmarket/cmd/mcpmarket-pp-cli@latest ``` If `--version` reports "command not found" after install, the runtime cannot see the binary directory on `$PATH`. Do not proceed with skill commands until verification succeeds. MCP Market has no official CLI today. This one mirrors the public catalog (servers, clients, Agent Skills) locally as you browse it, and because it's stateful across runs, it can answer questions the live website simply cannot: what's trending fastest, what changed since last week, and what one author has shipped across every entity type. ## When to Use This CLI Use this CLI to discover, compare, and track MCP servers, MCP clients, and Agent Skills — searching the catalog, reading full detail and SKILL.md content, and answering trend/history questions the live website can't. ## Anti-triggers Do not use this CLI for: - Do not use this CLI to connect a server to your own MCP Market organization or manage toolkits/team billing — that requires an authenticated account flow this CLI does not implement. - Do not use this CLI to actually install or run an MCP server on your machine — it surfaces install guidance, it does not execute installs. ## Unique Capabilities These capabilities aren't available in any other tool for this API. ### Local state that compounds - **`trending`** — See which MCP servers/skills are rising fastest vs. holding steady, computed from your own browse history. _Use this before picking a tool when momentum matters more than raw popularity._ ```bash mcpmarket-pp-cli trending --since 7d --json ``` - **`diff`** — See exactly which servers, clients, or skills were added, removed, or changed between two snapshots. _Use this to audit what changed in the catalog over a release cycle._ ```bash mcpmarket-pp-cli diff --from 2026-08-01 --to 2026-08-27 --json ``` - **`author`** — See everything one GitHub org has published across servers, skills, and clients in one view. _Use this to evaluate an author's full footprint before trusting one of their servers._ ```bash mcpmarket-pp-cli author mendableai --json ``` - **`leaderboard`** — See what the top-100 leaderboard looked like on a past date, not just right now. _Use this to answer 'what was trending three weeks ago' without external archives._ ```bash mcpmarket-pp-cli leaderboard --as-of 2026-08-01 --json ``` - **`watch category`** — Flag newly-appeared listings in a category since your last check. _Use this to stay current on a category you track without re-browsing it manually._ ```bash mcpmarket-pp-cli watch category "developer-tools" --json ``` - **`dedupe`** — Surface near-identical listings from different authors within a category. _Use this to avoid installing three servers that all do the same thing._ ```bash mcpmarket-pp-cli dedupe --category api-development --json ``` ### Agent-native plumbing - **`stack`** — Chain the similar-tools recommendation graph multiple hops to build a ranked shortlist around a server you already use. _Use this to discover a full toolchain, not just one related item at a time._ ```bash mcpmarket-pp-cli stack firecrawl --depth 2 --json ``` ## HTTP Transport This CLI uses Chrome-compatible HTTP transport for browser-facing endpoints. It does not require a resident browser process for normal API calls. ## Command Reference **category** — Catalog categories - `mcpmarket-pp-cli category` — List all catalog categories **mcpclient** — MCP clients (apps like Zed, Cline, Cherry Studio) listed on MCP Market - `mcpmarket-pp-cli mcpclient ` — Get details for one MCP client **server** — MCP servers listed on MCP Market - `mcpmarket-pp-cli server get` — Get details for one MCP server - `mcpmarket-pp-cli server similar` — Related/similar servers or skills **skill** — Agent Skills listed on MCP Market - `mcpmarket-pp-cli skill ` — Get details for one Agent Skill ### Finding the right command When you know what you want to do but not which command does it, ask the CLI directly: ```bash mcpmarket-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 ### Find the best PDF tool and see what it's related to ```bash mcpmarket-pp-cli server search "pdf" --json --select 0.name,0.url ``` narrow a broad search then feed a result's slug into stack ### Check who's trending in the last week ```bash mcpmarket-pp-cli trending --since 7d --json --select 0.name,0.delta ``` select just the fields that matter to avoid parsing a verbose payload ### See a server's full detail ```bash mcpmarket-pp-cli server get firecrawl --json ``` one call returns description, features, author, and related items ### Build a toolchain around a server you already use ```bash mcpmarket-pp-cli stack firecrawl --depth 2 --json ``` walks the similar-tools graph two hops out ### Audit an author's full footprint ```bash mcpmarket-pp-cli author mendableai --json ``` see every server, client, and skill one GitHub org has published (from what's been browsed locally) ## Auth Setup No authentication required. Run `mcpmarket-pp-cli doctor` to verify setup. ## Agent Mode Add `--agent` to any command. Expands to: `--json --compact --no-input --no-color`. - **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 mcpmarket-pp-cli category --agent ``` - **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: ```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 `MCPMARKET_HOME=` to relocate all four path kinds under one root. - Use per-kind env vars only when a specific kind must diverge: `MCPMARKET_CONFIG_DIR`, `MCPMARKET_DATA_DIR`, `MCPMARKET_STATE_DIR`, `MCPMARKET_CACHE_DIR`. - Resolution order is per-kind env var, `--home`, `MCPMARKET_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 `mcpmarket-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": { "mcpmarket": { "command": "mcpmarket-pp-mcp", "env": { "MCPMARKET_HOME": "/srv/mcpmarket" } } } } ``` Fleet precedence: an inherited per-kind env var overrides an explicit `--home` for that kind. Use `MCPMARKET_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 `MCPMARKET_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 mcpmarket-pp-cli recall "" --agent ``` **Pass the question through a file, not the shell.** As with `teach` (Step 4 below), the question may contain characters unsafe to interpolate into a shell argument — double quotes do **not** stop `` ` `` or `$(...)` command substitution. Write the question verbatim to a scratch file and pass `--query-file` instead of a positional argument whenever the question is not a short literal you wrote yourself: ```bash mcpmarket-pp-cli recall --query-file /tmp/mcpmarket-query.txt --agent ``` The response envelope: ```json { "query": "...", "normalized": "", "query_entities": ["..."], "found": true | false, "match_score": 0.0, "results": [ { "resource_id": "...", "resource_type": "...", "venue": "...", "confidence": 2, "entity_match": "exact|partial|unknown", "source": "taught|preseed|pattern", "warnings": ["..."] } ], "mismatches": [ /* only when --debug-mismatches */ ], "warnings": [ /* top-level */ ], "candidates": [ { "id": 12, "class": "flag_alias | playbook_candidate", "summary": "...", "sightings": 3, "last_seen": "...", "rationale": "...", "next_action": ["", "mcpmarket-pp-cli learnings confirm 12"] } ], "playbook": { "query_family": "...", "playbook": { "steps": [ { "cmd": "", "purpose": "..." } ], "entity_slots": ["$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 `mcpmarket-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; `mcpmarket-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 `mcpmarket-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. **Pass the question through a file, not the shell.** The user's question may contain characters that are unsafe to interpolate into a shell argument (`"`, `` ` ``, `$`, backslash, newlines). Do not build a shell string or heredoc to carry it — write the question verbatim to a local file using your own file-write capability, then pass that file's path to `--query-file`. Because the shell command below then contains only a static flag name and a static path, there is nothing in it for the user's text to escape or terminate: 1. Write the question, verbatim, to a scratch file (e.g. `/tmp/mcpmarket-query.txt`) using your file-write tool. 2. Invoke the CLI with `--query-file` pointing at that file: ```bash mcpmarket-pp-cli teach --query-file /tmp/mcpmarket-query.txt --resource-type --resource --resource & ``` (`--query ""` remains available for short, already-safe text — e.g. a fixed literal you wrote yourself, not raw user input — but `--query-file` is the recommended default since it has no shell-escaping surface at all.) 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