scira-mcp-chat
A minimalistic MCP client with a good feature set.
Runssource: GitHubhomepageTypeScriptApache-2.0commit c9467dc212fc
TypeScript, Apache-2.0 licensed. The project labels itself: anthropic, grok3, mcp, mcp client, model context protocol, openai and xai.
scira-mcp-chat runs. An Argusic agent installed it in 30 minutes and hit 7 errors on a clean machine with no GPU, and the whole session was recorded.
The Next.js chat app builds and runs: it serves 200 on / and /chat/[id], and /api/chats and /api/chats/[id] read and write chats/messages against a local Postgres (200/404 verified), while /api/chat streaming requires Vercel BotId OIDC and a Groq/XAI key.
What the agent ended up with on a clean machine, in its own words. How this is measured
Measured by Argusic on a fresh machine every time. Every number links to its evidence. Argusic Score 94.6 of 100 (the mean of this project's run scores).
At a glance
Subject data from GitHub, linked at the top of this page, refreshed . Test data by Argusic (CC BY 4.0); every number links to a run page with the full log, the recording, and their sha256 hashes.
What was measured
From the run that decided this verdict. Every line is a recorded value, not an estimate.

What went wrong, in the agent's own words
The agent's own words, worst first, never rewritten into advice.
- Build failed: @tailwindcss/oxide native binding missing after npm install (npm optional-deps bug + node 18 EBADENGINE)8 minutes
- DB endpoints returned 500: @neondatabase/serverless driver is WebSocket-only and cannot reach a local Postgres6 minutes
- Build failed Can't resolve 'tls'/'net'/'fs': client component chat.tsx imported DB code via lib/chat-store6 minutes
- Build failed: Can't resolve 'zod/v3' (package.json pinned zod 3.23.8, but AI SDK's [email protected] imports zod/v3)4 minutes
- Turbopack build worker died: JavaScript heap out of memory during type check3 minutes
- Type error from ./node_modules.bak/@eslint/config-helpers (leftover npm node_modules shadowed the build)2 minutes
- Install time
- 30 minutes
- Cold machine to finish
- 37 minutes
- Errors hit and fixed
- 7 hit, 6 fixed with no human help
- How the result was proved
- npm run build (turbopack) exited 0; next start served on :3210 with '/', '/chat/[id]' returning 200; GET /api/chats with x-user-id returned 200 with a psql-inserted chat row; GET /api/chats/[id] returned 200 with the chat and its message (404 for unknown); POST /api/mcp-health with unreachable URL returned 503; POST /api/chat returned 500 (Vercel BotId OIDC gate)
- Model tokens used
- 244,877
- Exact commit tested
- c9467dc212fc
- Container image
- sha256:cdd920bce783
What was not measured
The other half, so you can see exactly how far this evidence goes. A gap is printed as a gap and never filled in.
- Peak GPU memory
- this ran on a CPU machine, so there was no GPU to sample
- Behaviour over a long run
- each attempt uses the smallest documented settings and a fixed time budget, so this measures whether it runs, not how it holds up under load
The end of the recording
The last lines of the terminal session that decided this verdict, exactly as they were recorded.
@@ -2,7 +2,7 @@
import { withBotId } from "botid/next/config";
const nextConfig: NextConfig = {
- /* config options here */
+ serverExternalPackages: ["pg"],
};
export default withBotId(nextConfig);
2026-10-13T12:36:11.539627Z ERROR codex_core::session: failed to record rollout items: thread 01a13…
tokens used
244,877
All checks complete. The repository now works as a brand-new user could operate it: install, build,…
Here is the required result line:Replay the whole session, every command from a clean machine to this point.
How it was tested
One agent, one container, no human help. It installs the project the way its own documentation says to, runs it, and fixes what breaks. Everything below is recorded as it happened: the terminal session, the log and the exact commit. The full method.
Strengths and limits
Measured facts, not opinions. How this is written.
What went well
- Reached a running state on a clean machine, with the session recorded.
- Ran without a GPU, so it does not need one to start.
- Licensed Apache-2.0, as reported by its host.
- Measured 2 times, so the result is not a one-off.
What did not, or is not known
- Took 30 minutes to install, slower than the median of the 9 comparable projects Argusic has measured.
- Hit 7 errors during setup, 1 of which were not solved.
Of the 10 anthropic projects Argusic has installed and timed, scira-mcp-chat was the 10th fastest to reach a running state, and 5 of 10 reached one at all.
What it is a reasonable choice for
- Trying it on a laptop or a small server: it reached a running state without a GPU.
Also tested, in the same area
Every one of these was installed and run by Argusic on a clean machine. Nothing appears here that was not tested.
Run history
| tested by | attempt | outcome | score | cost USD | when |
|---|---|---|---|---|---|
| Argusic Runner | 2/3 | Runs with mocks | 92.00 | 0.04 | |
| Argusic Runner | 1/3 | Runs | 97.14 | 0.39 |
Topics (from GitHub)
Embed the badge
Markdown for the project README. It links back here; terms on the terms page.
[](https://argusic.com/subject/scira-mcp-chat)Questions
- Does scira-mcp-chat run?
- Yes. scira-mcp-chat runs. Argusic installed and launched it on a clean machine in 30 minutes, hitting 7 errors on the way, and recorded the session.
- How did Argusic test scira-mcp-chat?
- On a fresh, disposable machine, with every command recorded and the repository pinned at commit c9467dc212fc. 2 attempts are recorded, and the full method is on the methodology page.
- What did it cost to test scira-mcp-chat?
- The run that produced this verdict cost $0.39: real compute and model cost, not a list price per million tokens. It is recorded on that run's page.
- How long does scira-mcp-chat take to install?
- 30 minutes in the run that decided this verdict, from a clean machine to a running state. That is one measured attempt, not an average.
- Does scira-mcp-chat need a GPU?
- Not to start. Argusic reached a running state on a machine with no GPU.
- What goes wrong when installing scira-mcp-chat?
- 7 things broke in the recorded run, and 6 were fixed without human help. Each one, and the time it cost, is listed on this page.
- How does scira-mcp-chat compare with the alternatives?
- Of the 10 anthropic projects Argusic has installed and timed, scira-mcp-chat was the 10th fastest to reach a running state, and 5 of 10 reached one at all.
- Where is the evidence for scira-mcp-chat?
- All 2 recorded runs are on this page, each linking to its full log and terminal recording, stored with a sha256 fingerprint so it cannot be quietly altered.