Specula MCP Server
specula-org/Specula
[](https://agentrank-ai.com/tool/specula-org--Specula/?utm_source=badge&utm_medium=readme&utm_campaign=agentrank_badge) Specula: An agentic tool for finding deep bugs in system code using TLA+
claude mcp add agentrank -- npx -y agentrank-mcp-server Overview
specula-org/Specula is a Python agent tool licensed under Apache-2.0. Specula: An agentic tool for finding deep bugs in system code using TLA+
Ranked #482 out of 24846 indexed tools.
In the top 2% of all indexed tools.
Has 10 contributors.
Actively maintained with commits in the last week.
Ecosystem
Score Breakdown
524 stars → growing community
Last commit 5d ago → actively maintained
31/38 issues closed → responsive maintainer
10 contributors → active community
No dependents → no downstream usage
Weights: Freshness 20% · Issue Health 20% · Dependents 22% · Stars 10% · Contributors 8% · How we score →
Matched Queries
From the README
<p align="center">
<picture>
<source media="(prefers-color-scheme: dark)" srcset="pics/logo.png">
</picture>
</p>
<h2 align="center">
Scaling formal specs for autonomous bug finding
</h2>
<p align="center">
<a href="https://arxiv.org/abs/2607.25333">
</a>
<a href="https://github.com/specula-org/Specula/actions/workflows/ci.yml">
</a>
<a href="https://github.com/specula-org/Specula/blob/main/LICENSE">
</a>
</p>
Specula finds deep bugs in concurrent and distributed system code.
It uses coding agents to write TLA+ specs of the target system, including invariants that capture the system's correctness properties and formal models that describe the system implementation. It then model-checks the specs and reproduces violations at the code level. Specula has been used to find deep bugs in many open-source projects. For more details, see our [paper](https://arxiv.org/abs/2607.25333).
We maintain [a list of bugs found by Specula](https://docs.google. Read full README on GitHub → Get the weekly AgentRank digest
Top movers, new tools, ecosystem insights — straight to your inbox.