Forage vs MCPDiscovery
A side-by-side look at the Forage and MCPDiscovery MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Forage for aggregators work as a local process; choose MCPDiscovery for aggregators as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Forage when
- You need dedicated capabilities in the Aggregators domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
- You want tools like
forage_search, forage_evaluate, forage_install.
Choose MCPDiscovery when
- You need dedicated capabilities in the Aggregators domain.
- You prefer a local stdio subprocess transport.
- Its auth model fits you: No auth required.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Aggregators | Aggregators |
| Quality signal | 59/100 · Good | 43/100 · Fair |
| Install command | Confirmed | Confirmed |
| Transport | Local subprocess (stdio) | Local subprocess (stdio) |
| Auth | No auth required | No auth required |
| Pricing | Free | Free |
| Required env vars | None listed | None listed |
| Verified owner | Community listing | Community listing |
| GitHub stars | 19 | 53 |
| Directory activity | 7 views 0 installs 0 upvotes | 2 views 0 installs 0 upvotes |
| Tools | 6 | Not listed |
| Full listing | View Forage | View MCPDiscovery |
Tools & capabilities
Forage tools 6
forage_searchSearch for MCP servers and tools across registries (Official MCP Registry, Smithery, npm). Describe what capability you need and get ranked results.forage_evaluateGet detailed information about a specific package — version, downloads, README summary, install command. Use this before installing to verify quality.forage_installInstall an MCP server and start it as a proxied subprocess. The server's tools become available immediately via Forage — no restart needed. IMPORTANT: Set confirm=true to proceed with installation (user will be prompted to approve the tool call).forage_learnWrite usage instructions for an installed tool to agent rule files (CLAUDE.md, AGENTS.md, .cursor/rules/). This persists knowledge across sessions so the agent remembers how to use the tool next time.forage_statusList all tools that Forage has installed and is currently proxying. Shows which servers are running, what tools they provide, and their install status.forage_uninstallRemove a previously installed tool. Stops the server, removes from manifest, and cleans up agent rules. Set confirm=true to proceed.
MCPDiscovery tools
No tool names declared yet. Check the project README from the listing page.
Ready-to-paste client configs
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.
Forage
{
"mcpServers": {
"isaac-levine-forage": {
"command": "npx",
"args": [
"-y",
"forage-mcp"
]
}
}
}
MCPDiscovery
{
"mcpServers": {
"particlefuture-mcpdiscovery": {
"command": "npx",
"args": [
"-y",
"@1mcpserver/1mcpserver"
]
}
}
}
Frequently asked questions
Forage is categorized under Aggregators and uses a local stdio subprocess. MCPDiscovery belongs to Aggregators and uses a local stdio subprocess. Pick Forage for aggregators work and MCPDiscovery for aggregators.
Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.
Forage is listed as free. Auth: no auth required. MCPDiscovery is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.
Yes. MCP clients support multiple servers: add isaac-levine-forage and particlefuture-mcpdiscovery as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Forage has a quality signal of 59/100 (Good) with 7 views, 0 installs and 19 GitHub stars. MCPDiscovery has 43/100 (Fair) with 2 views, 0 installs and 53 GitHub stars.
