MCPEvol-Bench: Benchmarking LLM Agent Performance Across Dynamic Evolutions of M
As Model Context Protocol (MCP) servers emerge as the core infrastructure for connecting LLMs with external tools, existing benchmarks leverage real-world MCP servers to evaluate LLM agents' tool-using capabilities. However, these benchmark
https://arxiv.org/abs/2607.14642v1 ↗Thesis fit
Good fit
Within your typical scope; diligence still required.
In your usual scope
Idea match
Light
How close the company’s idea is to your thesis statement
Sector
agents, llm
Overlap with sectors you care about
Geography
Unknown
Location unknown — scores 0
Your thesis: “We back exceptional technical founders building AI-first products and infrastructure, deploying $100K checks within 24 hours.”
Founder → stable
Traction → stable
Idea vs market ↓ declining
▸ Add / edit details
Correct facts used on the next screening or memo.
People
H
Huanxi Liu
3.4
low confidence
K
Kun Hu
3.0
low confidence
J
Jiaqi Liao
1.0
low confidence
Q
Qiang Wang
2.0
low confidence
P
Pengfei Qian
2.0
low confidence
Y
YuanZhao Zhai
2.0
low confidence
D
Dawei Feng
2.0
low confidence
B
Bo Ding
2.0
low confidence
H
Huaimin Wang
2.0
low confidence
J
J G Liao
1.0
low confidence
Activity & evidence
Similar baseline plays (YC · idea space)
Manufact
· Active
Cloud infrastructure for MCP servers and Claude / ChatGPT apps.
founders not scraped yet