Hacker ApprovedDepartments

mcp2cli

Shares rank 28 of 86 privilege escalation tools by recommenders

Turns MCP servers and APIs into a command-line interface so agents discover tools on demand, which cuts token use. Critics raise the latency cost and say the docs read as generated.

Turns MCP servers and APIs into a command-line interface so agents discover tools on demand, which cuts token use. Critics raise the latency cost and say the docs read as generated.

15 people gave an opinion

recommend it
13
criticize it
2
approval share
87%
Each figure is one person. RecommendsCriticizes

Recommended in 1 of 13 months

  1. November 2025: not recommended
  2. December 2025: not recommended
  3. January 2026: not recommended
  4. February 2026: not recommended
  5. March 2026: recommended
  6. April 2026: not recommended
  7. May 2026: not recommended
  8. June 2026: not recommended
  9. July 2026: not recommended
  10. August 2026: not recommended
  11. September 2026: not recommended
  12. October 2026: not recommended
  13. November 2026: not recommended (month in progress)

Why it doesn’t carry the badge

  • 13 people recommend itNeeds 10 or more, met.
  • 6.5 recommenders for every criticNeeds 2 to 1 or better, met.
  • Recommended in 1 of 13 monthsNeeds 4 or more, not met.

The same three rules apply to every product, and the badge can’t be bought. How the badge works

What people say about it

The reasons people give, with the number of comments that give each one. Open a reason to read what they said.

Why people recommend it

Each mark is one comment

  • On-demand tool discovery instead of full schemas

    “on-demand discovery is genuinely smarter than front-loading every schema”

    Comment from 10 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

    “the on-demand discovery approach is the right design”

    Comment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

    “The lazy discovery pattern is clever.”

    Comment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”
  • Large token reduction

    “the token math is compelling but the latency tradeoff seems worth calling out”

    Comment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

    “The token reduction is a big deal.”

    Comment from 10 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

What people warn about

Each mark is one comment

  • Docs and prose read as generated

    “this is a cool idea but the prose in the readme and the above post seem to be fully generated”

    Comment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

    “This post and the project README are obviously generated slop, which personally makes me completely skip the project altogether”

    Comment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

Other privilege escalation tools people recommend

The four most recommended other privilege escalation tools, with the same counts for each, so you can compare like for like. The tick on each bar marks the 2 to 1 line the badge needs.

mcp2cli compared with 4 alternatives
ProductRecommendCriticizeApprovalMonthsOwnedBadge
fzf78594%12—Approved
jq753369%12—Approved
grep651977%12—Approved
Atuin632472%112 yrs4 ownersApproved
mcp2cliThis page13287%1——
See all 86 privilege escalation tools, ranked

What people said

13 of the 15 comments that mention it, newest first. Each links to the original comment.

“Great tool, however we went to a dedicated CLI client”

MixedComment from 16 Mar 2026 in “MCP Server Is Eating Your Context Window. There's a Simpler Way”

“There's already an open source tool that does exactly the same thing”

RecommendsComment from 16 Mar 2026 in “MCP Server Is Eating Your Context Window. There's a Simpler Way”

“The token reduction is a big deal.”

RecommendsComment from 10 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“on-demand discovery is genuinely smarter than front-loading every schema”

MixedComment from 10 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“the on-demand discovery approach is the right design”

MixedComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“I was inspired by clihub (I credited them) but I also wanted 3 additional things.”

RecommendsComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“The lazy discovery pattern is clever.”

RecommendsComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“the token math is compelling but the latency tradeoff seems worth calling out”

MixedComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“Doubtful that a 16 tokens summary is the same as she JSON tool description that uses 10x more tokens”

CriticizesComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“This post and the project README are obviously generated slop, which personally makes me completely skip the project altogether”

CriticizesComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“which I think is the strongest benefit for high capability agents”

RecommendsComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“this is a cool idea but the prose in the readme and the above post seem to be fully generated”

MixedComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

“Something more general like this clearly has more utility.”

RecommendsComment from 9 Mar 2026 in “Show HN: Mcp2cli – One CLI for every API, 96-99% fewer tokens than native MCP”

Counts come from 1,795,640 Hacker News comments, November 2025 to November 2026. How we count. Report a mistake.