A side-by-side look at the Pinlyx MCP and Webclaw MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Pinlyx MCP for social media work as a local process; choose Webclaw for other tools and integrations as a local process. You can also run both side by side in one mcpServers block.
CRMSOLID_API_KEY.crm_list_social_accounts, crm_list_social_conversations, crm_get_social_conversation.scrape, crawl, map.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Social Media | Other Tools and Integrations |
| Quality signal | 82/100 · Excellent | 71/100 · Great |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | API key required | No auth required |
| Pricing | Freemium | Free |
| Required env vars | CRMSOLID_API_KEY | None listed |
| Verified owner | Verified | Community listing |
| GitHub stars | 5 | 2,373 |
| Directory activity | 8 views 0 installs 0 upvotes | 13 views 2 installs 0 upvotes |
| Tools | 13 | 10 |
| Full listing | View Pinlyx MCP | View Webclaw |
crm_list_social_accountsLists connected accounts per platformcrm_list_social_conversationsFilters by `platform`, `status`, `contactId`, `unreadOnlycrm_get_social_conversationOne conversation plus its last 10 messagescrm_list_social_messagesMessage history, paged with `beforeMessageIdcrm_send_social_messageSends a DM and pauses the AI agent for that contactcrm_mark_social_conversation_readClears unread state, safe to repeatcrm_social_inbox_summaryTotals per platform, plus the 10 oldest waiting repliescrm_list_social_postsFilters by `status`, `platform`, `fromDate`, `toDatecrm_get_social_postOne post with its media, target account and outcomecrm_schedule_social_postQueues a post per target account, **never publishes by accidentcrm_update_social_postEdits content, time or media while the post is still pendingcrm_cancel_social_postCancels a post that has not gone outscrapeExtract one URL as markdown, text, JSON, LLM format, or HTMLcrawlFollow same-origin links and extract discovered pagesmapDiscover URLs without extracting every pagebatchScrape multiple URLs in parallelextractConvert page content into structured datasummarizeSummarize a pagediffCompare page content snapshotsbrandExtract colors, fonts, logos, and metadatasearchSearch the web and scrape resultsresearchMulti-source research workflowPaste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.
{
"mcpServers": {
"crm-solid-mcp": {
"command": "npx",
"args": [
"-y",
"@crmsolid/mcp-server"
],
"env": {
"CRMSOLID_API_KEY": "YOUR_CRMSOLID_API_KEY_HERE"
}
}
}
}
{
"mcpServers": {
"0xmassi-webclaw": {
"command": "npx",
"args": [
"-y",
"create-webclaw"
]
}
}
}