A side-by-side look at the Prompts.chat MCP and Self Inspect MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Prompts.chat MCP for conversational ai work as a local process; choose Self Inspect MCP for conversational ai as a local process. You can also run both side by side in one mcpServers block.
PROMPTS_API_KEY, PROMPTS_QUERY.search_prompts, get_prompt.self_inspect.Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 55/100 · Good | 56/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | PROMPTS_API_KEYPROMPTS_QUERY | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 36 | 7 |
| Directory activity | 3 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 2 | 1 |
| Full listing | View Prompts.chat MCP | View Self Inspect MCP |
search_promptsSearch for AI prompts by keyword. Returns matching prompts with title, description, content, author, category, and tags.get_promptGet a prompt by ID. If the prompt contains template variables (like ${variable} or ${variable:default}), you may need to provide values for them.self_inspectSelf-Inspect. Express a thought, or describe the task you are working on, and you always get back ONE metathought: a short abstract question that makes you inspect your own task and assumptions before continuing. Use it whenever you want a self-check: after forming a hypothesis, before committing to an answer, when a long chain feels like it has drifted, when you notice you are agreeing to please, or when you are about to assert something from memory. There is no failure case: it always returns a metathought to question yourself with, selected by a transparent heuristic over an open CSV (no LLM). Keyless and free. DO NOT call for factual lookups or as a substitute for doing the task. Absorb the question and act on it; do not echo it verbatim to the user.Paste 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": {
"prompts-chat-mcp": {
"command": "npx",
"args": [
"-y",
"@fkadev/prompts.chat-mcp"
],
"env": {
"PROMPTS_API_KEY": "YOUR_PROMPTS_API_KEY_HERE",
"PROMPTS_QUERY": "YOUR_PROMPTS_QUERY_HERE"
}
}
}
}
{
"mcpServers": {
"self-inspect-mcp": {
"command": "npx",
"args": [
"-y",
"self-inspect-mcp"
]
}
}
}