Chimera Forge MCP Server

A local-first, model-agnostic LLM deployment planner. It turns "which model, quantization, GPU, and backend -- how many, will it fit, will it hit my SLO, what will it cost" into a fast, honest, measured answer, from your shell, your Python, or your AI assistant.

People who work with benchmarking, ollama and performance and want it reachable from Claude, Cursor, VS Code, or another MCP client. The project is written in Python.

VERIFIED ACTIVE

LAST COMMIT 2026-09-15 · ★ 2 · #15 OF 106 MAINTAINED AI & ML · VERIFIED 2026-09-18

MIT · Python servers · how we verify → /methodology

01 · Install Chimera Forge

Claude Code

claude mcp add sahil170595-chimeraforge -- uvx chimeraforge

Claude Desktop / Cursor / VS Code - add to config

{
  "mcpServers": {
    "sahil170595-chimeraforge": {
      "command": "uvx",
      "args": [
        "chimeraforge"
      ]
    }
  }
}

Same JSON for Cursor. For VS Code, rename the top-level key from `mcpServers` to `servers`.

Using another client? Same JSON, different key

Claude Desktop · mcpServers

Cursor · mcpServers

VS Code · servers

Windsurf · mcpServers

Zed · context_servers

Cline · mcpServers

Roo Code · mcpServers

Continue · mcpServers

LibreChat · mcpServers

Gemini CLI · mcpServers

Codex CLI · mcp_servers

Full setup guides: every client.

02 · Evidence

Security posture

What to check before giving this server access to your agent - from the registry, GitHub, and our own probes. We don't score safety; we show what's verifiable.

runs as local process (stdio) - runs on your machine with your user's permissions

license MIT - declared in the repository

pypi package chimeraforge - check the name against the project README before installing (PyPI has no namespace ownership)

registry namespace io.github.Sahil170595 is GitHub-verified and matches the repo owner

03 · What Chimera Forge can do

Prose above is summarized from the project's README and registry record - no invented capabilities.

Latest releases

v0.34.0 · 2026-09-15

Phase 8 item P8.6, sub-items 1-3 and 5 (#66). The GPU table was the last hand-typed dataset in the product, and it drives more of the answer than any other, since decode is modelled as bandwidth-bound. · Added · An…

v0.33.0 · 2026-09-15

Phase 8 item P8.4 (#65). The quality gate is the planner's cleanest differentiator - nobody else rejects a quantization level on quality before touching hardware - and it was built on the corpus's weakest data. · Added…

v0.32.0 · 2026-09-15

Phase 8 item P8.3 (#64). Two corrections to time-to-first-token, both derivations rather than fits. · Added · plan --max-num-batched-tokens N: chunked prefill. vLLM V1 enables chunked prefill by default…

04 · Who maintains Chimera Forge

ChimeraForge is maintained by sahil170595. It's the only MCP server we track from this author; the repo dates to Nov 2025.

05 · Facts

repository
github.com/sahil170595/chimeraforge
category
AI & ML - ranked #15 of 106 actively-maintained AI & ML servers as of 2026-09-18.
release cadence
10+ releases in the last 90 days (latest 2026-09-15)
registry
io.github.Sahil170595/chimeraforge (active, first published 2026-08-12 · 35 versions)
packages
pypi:chimeraforge

06 · Chimera Forge FAQ

What is Chimera Forge?

A local-first, model-agnostic LLM deployment planner. It turns "which model, quantization, GPU, and backend -- how many, will it fit, will it hit my SLO, what will it cost" into a fast, honest, measured answer, from your shell, your Python, or your AI assistant.

Is Chimera Forge still maintained?

Yes - as of 2026-09-18, its last commit was 2026-09-15 and it shipped 10+ releases in the last 90 days. We re-verify nightly.

How do I install Chimera Forge?

Run `uvx chimeraforge`. You can also paste the ready-made client config above.

Does Chimera Forge run locally?

Yes - it's a stdio server: it runs on your machine (via uvx) with your user's permissions. Your data stays local unless the server itself calls external APIs.

07 · Alternatives to Chimera Forge

Alternatives to Chimera Forge

Maintained AI & ML servers if Chimera Forge isn't the fit.

  1. Fun ASR Transcribe local audio with FunASR and SenseVoice using private, on-device inference. ★ 20,411 · 2026-09-18
  2. Auto TS Automated time series forecasting with model search, anomaly detection, and event risk analysis ★ 1,428 · 2026-08-25
  3. Haiku RAG Local-first agentic RAG with citations - hybrid search, reranking, multimodal document retrieval ★ 609 · 2026-09-17
  4. Plan Exe MCP server for generating rough-draft project plans from natural-language prompts. ★ 401 · 2026-09-13
  5. Local RAG (shinpr) Easy-to-setup local RAG server with minimal configuration ★ 398 · 2026-09-18
  6. PageIndex MCP Reasoning-based RAG system for chatting with long PDFs. Supports local and online files. ★ 388 · 2026-07-25

Pairs well with

Servers that cover what Chimera Forge doesn't - only shown when the pairing reason fits the companion.

  1. Codebase Memory → memory companion memory · ★ 43,715
  2. Memorix → memory companion memory · ★ 785
  3. Supabase → database companion database · ★ 2,910
  4. MongoDB MCP Server → database companion database · ★ 1,131

More AI & ML MCP servers · Dev Globe · Yahboom MCP · Agent Forge · Codeweave · Minirag MCP

More Python MCP servers · Saidsef MCP GitHub PR Issue Analyser · The Undesirables TCG Oracle · Maven Decoder · AEC Model Bridge · Autodesk Revit MCP Server · see all