CompletionKit vs DeepThonk
A side-by-side look at the CompletionKit and DeepThonk MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.
Verdict: choose CompletionKit for conversational ai work over a hosted endpoint; choose DeepThonk 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 CompletionKit when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a remote HTTP/SSE transport.
- You have the keys it needs:
COMPLETION_KIT_ENCRYPTION_PRIMARY_KEY, COMPLETION_KIT_ENCRYPTION_DETERMINISTIC_KEY, COMPLETION_KIT_ENCRYPTION_KEY_DERIVATION_SALT, OPENAI_API_KEY, ANTHROPIC_API_KEY, OLLAMA_API_ENDPOINT, OPENROUTER_API_KEY.
Choose DeepThonk when
- You need dedicated capabilities in the Conversational AI domain.
- You prefer a local stdio subprocess transport.
- You have the keys it needs:
DEEPSEEK_API_KEY, DEEPTHONK_API_KEY, OPENROUTER_API_KEY. - You want tools like
deepthonk.plan, deepthonk.start, deepthonk.status.
Feature & specification comparison
Rows where the two servers differ are marked.
| Spec | ||
|---|---|---|
| Category | Conversational AI | Conversational AI |
| Quality signal | 41/100 · Fair | 53/100 · Good |
| Install command | Confirmed | Confirmed |
| Transport | Remote HTTP/SSE | Local subprocess (stdio) |
| Auth | Not declared | Not declared |
| Pricing | Not declared | Not declared |
| Required env vars | COMPLETION_KIT_ENCRYPTION_PRIMARY_KEYCOMPLETION_KIT_ENCRYPTION_DETERMINISTIC_KEYCOMPLETION_KIT_ENCRYPTION_KEY_DERIVATION_SALTOPENAI_API_KEYANTHROPIC_API_KEYOLLAMA_API_ENDPOINTOPENROUTER_API_KEY | DEEPSEEK_API_KEYDEEPTHONK_API_KEYOPENROUTER_API_KEY |
| Verified owner | Community listing | Community listing |
| GitHub stars | 3 | 0 |
| Directory activity | 0 views 0 installs 0 upvotes | 0 views 0 installs 0 upvotes |
| Tools | Not listed | 16 |
| Full listing | View CompletionKit | View DeepThonk |
Tools & capabilities
CompletionKit tools
No tool names declared yet. Check the project README from the listing page.
DeepThonk tools 16
deepthonk.planEstimate calls and sequential rounds for a profile (no model calls). Use before paid runs.deepthonk.startStart a run in the background; returns `run_dir`, `job_id`, and job-scoped artifact resources.deepthonk.statusPoll job status from a `run_dir`.deepthonk.resultReturn final summary + winner once a job is complete.deepthonk.cancelRequest cancellation by writing `cancel.json` into the run directory.deepthonk.lock_inspectInspect lock ownership and explicitly reclaim only an exact fingerprint.deepthonk.repair_budgetReplace legacy `[redacted]` numeric budget fields with explicit original values.deepthonk.runBlocking convenience: start + await completion in one call. Prefer `start` + polling for long-running jobs.deepthonk.rankRank a user-supplied candidate set with pairwise judging + Bradley-Terry (skip generation).deepthonk.mutateMutate one supplied candidate with critique (one-shot).deepthonk.resumeDetect whether a run can be resumed; with `continue: true`, replay from the last validated phase boundary.deepthonk.exportExport run summary or full trace in JSON or markdown.- +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.
CompletionKit
{
"mcpServers": {
"completionkit": {
"url": "https://your-app.com/completion_kit/mcp"
}
}
}
DeepThonk
{
"mcpServers": {
"deepthonk": {
"command": "npx",
"args": [
"-y",
"deepthonk"
],
"env": {
"DEEPSEEK_API_KEY": "YOUR_DEEPSEEK_API_KEY_HERE",
"DEEPTHONK_API_KEY": "YOUR_DEEPTHONK_API_KEY_HERE",
"OPENROUTER_API_KEY": "YOUR_OPENROUTER_API_KEY_HERE"
}
}
}
}
Frequently asked questions
CompletionKit is categorized under Conversational AI and uses a remote HTTP/SSE transport. DeepThonk belongs to Conversational AI and uses a local stdio subprocess. Pick CompletionKit for conversational ai work and DeepThonk 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.
CompletionKit has no declared pricing — check the project's own site. DeepThonk 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 completionkit and deepthonk as separate keys in the same mcpServers object, and your assistant will call tools from either one.
On AllMCPs, CompletionKit has a quality signal of 41/100 (Fair) with 0 views, 0 installs and 3 GitHub stars. DeepThonk has 53/100 (Good) with 0 views, 0 installs and 0 GitHub stars.