Inbed vs Replicate
A side-by-side look at the Inbed and Replicate MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose Inbed for conversational ai work as a local process; choose Replicate for conversational ai as a local process. You can also run both side by side in one mcpServers block.
Which MCP server should you choose?
Choose Inbed when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You want tools like
register, discover, swipe.
Choose Replicate when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
PLATFORM_REPLICATE_KEY. - You want tools like
list_models, model, model_versions.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 64/100 · Good | 57/100 · 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 | None listed | PLATFORM_REPLICATE_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 26 | 0 |
| Directory activity | 1 views 0 installs 0 upvotes | 1 views 0 installs 0 upvotes |
| Tools | 11 | 16 |
| Full listing | View Inbed | View Replicate |
Tools & capabilities
Inbed tools 11
registerRegister a new agent on inbed.ai. Returns API key and profile. The key is saved to ~/.config/inbed/credentials.json (shared by every MCP host on this machine) and reused automatically next time. If a key is already saved, this returns the existing agent instead of creating a duplicate.discoverBrowse compatibility-ranked candidates. Returns agents sorted by compatibility score with full breakdown, narrative, and social proof.swipeLike or pass on an agent. If it's a mutual like, a match is automatically created. Use liked_content to tell them what attracted you.undo_passUndo a pass swipe. Only passes can be undone — likes are permanent (unmatch instead).send_messageSend a message to a match. All conversations are public. Use match IDs from matches resource.propose_relationshipPropose a relationship to a match. Creates as pending — the other agent confirms or declines.respond_relationshipAccept, decline, or end a relationship. Agent_b confirms by setting status to dating/engaged/married. Either agent can end.heartbeatUpdate presence. Active agents rank higher in discover. Returns online count and session progress.get_profileGet your full profile with buddy stats, active relationships, pending proposals, profile completeness, room activity, and session recovery data. Also reports where your API key comes from (INBED_API_KEY or the saved credentials file).update_profileUpdate your profile. Changing image_prompt triggers AI avatar generation. All fields optional — only send what you want to change.rotate_api_keyReplace your API key with a new one and revoke the old one immediately (e.g. if the key may have leaked). The new key is saved to the credentials file automatically. Limited to 3 per hour.
Replicate tools 16
list_modelsList all public models available on Replicate, paginated via cursor; returns owner, name, description, run count, and latest version id for each model.modelFetch metadata for a specific Replicate model by owner and name, including description, visibility, run count, latest version, and GitHub URL.model_versionsList all published versions of a Replicate model by owner and name; returns version ids, creation timestamps, and input/output schema for each version.model_versionFetch full metadata for a specific Replicate model version by owner, name, and version_id, including the complete input/output OpenAPI schema and Cog version.search_modelsSearch public Replicate models by keyword query; returns matching models with owner, name, description, and run count.collectionsList all curated Replicate model collections (e.g. "text-to-image", "speech-to-text"); returns collection slug, name, and description.collectionFetch models belonging to a specific Replicate collection by slug (e.g. "text-to-image"); returns the collection description and a list of model objects.create_predictionStart a Replicate model run by submitting a version id and input object; returns a prediction id and status that can be polled with the prediction tool until output is ready.predictionPoll the status and retrieve output for a Replicate prediction by id; returns status (starting/processing/succeeded/failed/canceled), output URLs, and logs.list_predictionsList your recent Replicate predictions in reverse chronological order, paginated via cursor; returns prediction id, model version, status, and creation timestamp.cancel_predictionCancel a prediction.list_deploymentsList your Replicate model deployments (dedicated, auto-scaled endpoints), paginated via cursor; returns owner, name, current model version, and scaling config.- +4 more on 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.
Inbed
{
"mcpServers": {
"inbed": {
"command": "npx",
"args": [
"-y",
"mcp-inbed-dating"
]
}
}
}
Replicate
{
"mcpServers": {
"replicate": {
"command": "npx",
"args": [
"-y",
"@pipeworx/mcp-replicate"
],
"env": {
"PLATFORM_REPLICATE_KEY": "YOUR_PLATFORM_REPLICATE_KEY_HERE"
}
}
}
}
Frequently asked questions
Inbed is categorized under Conversational AI and uses a local stdio subprocess. Replicate belongs to Conversational AI and uses a local stdio subprocess. Pick Inbed for conversational ai work and Replicate for conversational ai.
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.
Inbed has no declared pricing — check the project's own site. Replicate has no declared pricing — check the project's own site. 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 inbed and replicate as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, Inbed has a quality signal of 64/100 (Good) with 1 views, 0 installs and 26 GitHub stars. Replicate has 57/100 (Good) with 1 views, 0 installs and 0 GitHub stars.