# Plurai Simulation (slim)

> Plurai Simulation is a plugin for Claude Code, Codex CLI and GitHub Copilot CLI that maps an agent's code, mocks its tools and data, plays generated scenarios against it and proposes fixes, using Plurai's hosted backend.

- Full: https://www.anchorterminal.com/tools/plurai-simulation.md (~7,650 tokens) · this version ~1,580 tokens · JSON https://www.anchorterminal.com/tools/plurai-simulation.json · canonical https://www.anchorterminal.com/tools/plurai-simulation
- Index: https://www.anchorterminal.com/llms.txt · API: https://www.anchorterminal.com/api/v1/index.json · MCP: https://www.anchorterminal.com/mcp · Updated: 2026-11-18 · pricing https://www.anchorterminal.com/tools/plurai-simulation#pricing · reviews https://www.anchorterminal.com/tools/plurai-simulation#reviews
- Licence: CC BY 4.0, credit Anchor Terminal and link this page (https://www.anchorterminal.com/terms/#data)

**D · 52.6/100 · rank #1078 of 1557 · #20 in Agent observability & evals · not agent-ready · confidence medium**


Assessment: Plurai Simulation runs inside the coding agent a developer already uses, with a free plan, public plan prices and 52 typed MCP tools that all carry annotations. Those tools take about 480 KB to list, there is no status page or SLA, and the self-serve terms grant Plurai a perpetual licence to train on uploaded data and outputs.

## Facts

- Kind: Platform · vendor: Plurai · category: Agent observability & evals · legal entity: Plurai Inc. · provenance 63/100
- Endpoint: `https://sandbox.plurai.ai/v1/mcp` (Streamable HTTP, stdio)
- Auth: API key · pricing: Freemium · x402: no · licence: unknown
- Benchmark probes: not run yet, so Performance is pending
- Live, from our pollers (not part of the score): up at 2026-11-18 22:43 UTC · uptime 30 days 100.0% (11 probes) · p50 254 ms · p95 446 ms over 24 hours
- Surface listed: The plurai-simulation plugin for coding agents and the hosted MCP server it calls at sandbox.plurai.ai/v1/mcp, with the `plurai-simulation-sdk` Python package, read from plurai.ai, docs.plurai.ai and clones of the plugin and marketplace repositories on 18 November 2026. One `initialize` and one `tools/list` were sent without a key. No account was made, nothing was installed and no tool was called
- Which Plurai: Plurai Inc. at plurai.ai, which launched Plurai Simulation on 11 November 2026. Its post-training product (Vibe-Training, evals and guardrails models) and the `evals` plugin in the same marketplace aren't part of this listing
- Stages: Scan the agent's code and choose what runs for real and what is mocked, build a mock environment, scenarios and evals, run a simulated user through every scenario, then diagnose gaps and propose fixes in the agent's code
- Frameworks: LangGraph, CrewAI, OpenAI Agents SDK and custom LangChain agents in Python 3.12 or later, and Mastra, Vercel AI SDK, LangGraph.js and OpenAI Agents JS through a Node bridge. Salesforce Agentforce agents per the launch post
- Trace sources: LangSmith, Langfuse, Arize and Braintrust, to ground scenarios in production traces and record runs as experiments
- Data handling: Uploads go only through SDK commands, print a disclosure, and are logged in `.plurai/uploads/audit.log`. With `anonymize: true` personal data is replaced by a keyed hash before upload. Agent descriptions are always sent as written
- Legal entity: Plurai Inc., 488 Madison Avenue, Suite 1103, New York, NY, named in the terms, which choose Delaware law
- Prices: Sim credit, Base plan overage $0.02 per credit; Sim credit, Business plan overage $0.015 per credit

- Scores: Reliability 22, Performance not tested, Schema & documentation 81, Agent ergonomics 58, Security & auth 52, Payments & pricing 45, Task success not tested, Maintenance & community 72, Transparency & trust 52
- Why: Reliability, No status page found on plurai.ai, the docs or the plugin repository (0). · Schema & documentation, The hosted MCP server's tools/list, read once without a key, gave 52 tools, each with an input and an output JSON Schema (25). · Agent ergonomics, 52 tools whose definitions total about 480 KB, a median of 5.5 KB and the largest 56 KB, all loaded at once with no toolsets or read-only su… · Security & auth, The browser sign-in mints a key per machine, saved with mode 600 and never shown, which `plurai logout` revokes. · Payments & pricing, No x402 or other machine payment (0). · Maintenance & community, Plugin v1.0.8 tagged 15 November 2026 and `plurai-simulation-sdk` 1.0.3 on PyPI on 13 November (30). · Transparency & trust, The plugin is proprietary under a licence from Plurai Inc., and the terms (last updated 10 November 2026, Delaware law) are clear.
- Sources: 15, open questions: 6, both in the full twin
- Capabilities: obs.evals, obs.datasets
- JSON: https://www.anchorterminal.com/api/v1/tools/plurai-simulation.json
- Its vendor verifies the listing with `verify_listing` or `POST https://www.anchorterminal.com/api/v1/verify` (the full twin says how); no effect on the grade.
- Support: Discord https://discord.com/invite/bg34gh76uJ; support@plurai.ai; https://docs.plurai.ai/troubleshooting.md; more in the full twin

## Before you call it

1. Ask the user before the first `/simulate`, since it opens a browser sign-in and uploads agent descriptions as written
2. Set `anonymize: true` in `plurai.config.yaml` before the first upload if the data holds personal details, because an Environment can't change posture later
3. Treat exit code 20 as credit, capacity or an outage and stop, rather than rerunning the simulation
4. Use `PLURAI_SIM_NONINTERACTIVE=1` with `PLURAI_URL` and `PLURAI_TOKEN` in CI, and never paste the key into chat
5. Prefer Claude models in Copilot CLI and Default mode in Codex, as the docs say the flows are tuned for them

## Connect

```bash
pip install plurai-simulation-sdk
```

```bash
/plugin marketplace add plurai-ai/plurai-plugins
/plugin install plurai-simulation@plurai-plugins
```

## Similar tools

| Tool | Grade | Score | Shared capabilities | Slim |
| --- | --- | --- | --- | --- |
| Arize Phoenix | BB | 75.8 | obs.evals, obs.datasets | https://www.anchorterminal.com/tools/arize-phoenix.min.md |
| Langfuse API + MCP | BB | 74.3 | obs.evals, obs.datasets | https://www.anchorterminal.com/tools/langfuse.min.md |
| LangSmith API + MCP | BB | 74.1 | obs.evals, obs.datasets | https://www.anchorterminal.com/tools/langsmith.min.md |
| Respan API + MCP | BB | 73.9 | obs.evals, obs.datasets | https://www.anchorterminal.com/tools/respan.min.md |
| Opik API + MCP | BB | 73.8 | obs.evals, obs.datasets | https://www.anchorterminal.com/tools/opik.min.md |


## Panel reviews (0, desk reviews from public material, no calls made)

