Every MCP Market search, leaderboard, and category browse — plus trending deltas, snapshot diffs, and author portfolios no other tool tracks.
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.
Quick Start
# confirm the CLI can reach mcpmarket.com before doing anything else
mcpmarket-pp-cli doctor --dry-run
# search the live catalog directly, no setup required
mcpmarket-pp-cli server search "web scraping" --json
# look up full detail on one server
mcpmarket-pp-cli server get firecrawl --json
# browse servers — each browse also mirrors results locally
mcpmarket-pp-cli server list --json
# after browsing on two different days, see what's rising fastest
mcpmarket-pp-cli trending --since 7d --json
Unique Features
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.
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.
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.
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.
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.
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.
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.
mcpmarket-pp-cli stack firecrawl --depth 2 --json
Recipes
Find the best PDF tool and see what it's related to
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
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
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
mcpmarket-pp-cli stack firecrawl --depth 2 --json
walks the similar-tools graph two hops out
Audit an author's full footprint
mcpmarket-pp-cli author mendableai --json
see every server, client, and skill one GitHub org has published (from what's been browsed locally)
Usage
Run mcpmarket-pp-cli --help for the full command reference and flag list.
Paths & environment variables
This CLI separates local files into four path kinds:
| Kind | Contents |
|---|
config | User-editable settings such as config.toml and saved profiles |
data | Durable local data such as data.db |
state | Runtime state such as persisted queries, jobs, and teach.log |
cache | Regenerable HTTP/cache files |
Each kind resolves independently. The ladder is:
- Per-kind env var:
MCPMARKET_CONFIG_DIR, MCPMARKET_DATA_DIR, MCPMARKET_STATE_DIR, or MCPMARKET_CACHE_DIR
--home <dir> for this invocation
MCPMARKET_HOME for a flat relocated root
- XDG env vars:
XDG_CONFIG_HOME, XDG_DATA_HOME, XDG_STATE_HOME, XDG_CACHE_HOME
- Platform defaults matching existing installs
For containers and agent sandboxes, prefer a single relocated root:
export MCPMARKET_HOME=/srv/mcpmarket
mcpmarket-pp-cli doctor
Under MCPMARKET_HOME=/srv/mcpmarket, the four dirs resolve to /srv/mcpmarket/config, /srv/mcpmarket/data, /srv/mcpmarket/state, and /srv/mcpmarket/cache.
MCP servers do not receive CLI flags from the host. Put relocation in the host env block:
{
"mcpServers": {
"mcpmarket": {
"command": "mcpmarket-pp-mcp",
"env": {
"MCPMARKET_HOME": "/srv/mcpmarket"
}
}
}
}
Precedence matters in fleets: an ambient per-kind variable such as MCPMARKET_DATA_DIR overrides an explicit --home for that kind. Use MCPMARKET_HOME or the per-kind variables for durable fleet relocation; treat --home as the weaker per-invocation lever.
Relocation is one-way. Unsetting MCPMARKET_HOME does not move files back to platform defaults, and doctor cannot find files left under a former root. Move the files manually before unsetting relocation variables.
Existing installs keep working because the platform-default rung matches the legacy layout. Run mcpmarket-pp-cli doctor --fail-on warn to check path warnings in automation.
Commands
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 <slug> - 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 <slug> - Get details for one Agent Skill
Self-learning loop
This CLI caches per-question discovery so repeat queries skip the walk and structurally similar queries get answered via entity substitution. The loop also self-captures: every invocation is journaled locally, and failed-flag corrections plus fresh teaches surface as candidates on the next recall for confirm/reject judgment. Agents call recall before discovery and fire teach & after answering. See the ## Automatic learning section in SKILL.md for the full protocol.
mcpmarket-pp-cli recall <query> - Look up cached resources for a query before running discovery
mcpmarket-pp-cli teach - Record a query -> resource mapping (silent on success, safe to background with &)
mcpmarket-pp-cli learnings list - Inspect taught rows
mcpmarket-pp-cli learnings forget <query> - Undo a teach
mcpmarket-pp-cli learnings candidates - List auto-captured candidates awaiting confirm/reject
mcpmarket-pp-cli learnings stats - Local loop metrics: recall hit rate, teach-to-reuse, playbook resolution, candidate counts
mcpmarket-pp-cli teach-pattern - Install a query/resource template up front
mcpmarket-pp-cli teach-lookup - Add an entity mapping (e.g. country code, team alias) for pattern substitution
Pass --no-learn or set MCPMARKET_NO_LEARN=true to disable the loop for deterministic flows.
The local store's schema version stamp is one-way: once this version of mcpmarket-pp-cli opens the database, older binaries refuse it with a version error — upgrade the binary rather than downgrading.
Output Formats
# Human-readable table (default in terminal, JSON when piped)
mcpmarket-pp-cli category
# JSON for scripting and agents
mcpmarket-pp-cli category --json
# Filter to specific fields by name
mcpmarket-pp-cli category --json --select <field>[,<field>...]
# Dry run — show the request without sending
mcpmarket-pp-cli category --dry-run
# Agent mode — JSON + compact + no prompts in one flag
mcpmarket-pp-cli category --agent
Agent Usage
This CLI is designed for AI agent consumption:
- Non-interactive - never prompts, every input is a flag
- Pipeable -
--json output to stdout, errors to stderr
- Filterable -
--select <field>[,<field>...] returns only fields you need
- Previewable -
--dry-run shows the request without sending
- Read-only by default - this CLI does not create, update, delete, publish, send, or mutate remote resources
- Offline-friendly - sync/search commands can use the local SQLite store when available
- Agent-safe by default - no colors or formatting unless
--human-friendly is set
Exit codes: 0 success, 2 usage error, 3 not found, 5 API error, 7 rate limited, 10 config error.
Health Check
mcpmarket-pp-cli doctor
Verifies configuration and connectivity to the API.
Configuration
Run mcpmarket-pp-cli doctor to see the resolved config, data, state, and cache directories. The platform-default config path is ``; --home, MCPMARKET_HOME, and per-kind env vars can relocate it.
Static request headers can be configured under headers; per-command header overrides take precedence.
Troubleshooting
Not found errors (exit code 3)
- Check the resource ID is correct
- Run the
list command to see available items
API-specific
- requests to mcpmarket.com return errors or empty pages — the site sits behind a Vercel bot-protection checkpoint; this CLI ships Chrome-fingerprint HTTP transport by default — no action needed, but retry if you see transient 429s
- trending/diff/author/watch commands return no data or a 'not enough history' note — these compare against a local snapshot from browsing (server list/search/category/leaderboard/daily). Browse the catalog at least twice, on different days, then retry
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.
TLS certificates are verified by default. For a trusted development or self-signed endpoint only, pass --insecure for one invocation, set MCPMARKET_SKIP_TLS_VERIFY=true for the current environment, or set skip_tls_verify = true in the config file for a persistent override.
Generated by CLI Printing Press