Perspect MCP server
online · 100% uptimecom.tryperspect/perspect·v1.0.0Convene a panel of expert AI personas to debate any decision from every side.
0 stars
Reviews
Write oneNobody has reviewed Perspect yet.
If you have run it, two minutes of your experience saves the next person an afternoon.
Perspect tools (2, 1 write)
write = sends, deletes, buys or postslist_personasFreeList the expert personas available to sit on a Perspect AI panel (id, name, discipline).
run_debatewrite actionFreeConvene a panel of expert personas to debate a topic, idea, or decision from conflicting angles, then return the debate, a contradiction map (where the experts disagree), and a synthesized briefing. Optionally pass specific persona ids (see list_personas); omit to auto-select a fitting panel. Takes ~30-60s.
Public scan report
scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it
- –Code scanremote-only server, no package to scann/a
- Live reliabilityremote reachable in 762ms20/20
- Tool poisoning2 tool descriptions checked15/15
- Auth qualityAPI key sent as a header8/15
- Maintenancelast push 38 days ago12/15
- Maintainer identitynamespace and repository owner differ; GitHub account older than a year5/10
How Perspect compares
Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.
- Safety score
- 80/100
- higher than 60% of 48,243 servers
- Tools
- 2
- the typical server has 7
- Tools that change things
- 50%
- typical: 0%. Fewer write tools means less an agent can break
- Uptime
- 100%
- of our recent checks; the typical remote server answers 100%
- Response time
- 97 ms
- faster than 84% of 30,027 servers
What its tools let an agent do: 1 read · 1 run or deploy
Install Perspect in Claude Code, Cursor or VS Code
claude mcp add --transport http perspect https://perspect-ai-backend.onrender.com/mcp
What the publisher says
From the Perspect repository's README, as published. We do not edit it. Read it on GitHub
Perspect , Claude Code plugin
Convene a panel of expert AI personas to debate any topic, idea, or decision, from every side. Perspect runs the debate, cites live web sources, maps exactly where the experts disagree, and hands back a synthesized briefing. Not a yes-man.
Install
/plugin marketplace add Nkbros12k/perspect-mcp
/plugin install perspect-debate@perspectSet your token
The connector runs debates against your own Perspect account, so it needs a personal token (requires a Perspect Pro plan):
- Go to https://www.tryperspect.com/connect and click Generate key.
- Set it in your environment before using the plugin:
export PERSPECT_TOKEN=psk_your_key_here(or add PERSPECT_TOKEN=... to your shell profile / .claude/env.)
The plugin's MCP config reads ${PERSPECT_TOKEN} and sends it as Authorization: Bearer .
Tools
contradiction map, and a synthesized briefing (~30-60s).
- run_debate(topic, personas?) , convene the panel; returns the debate, the
- list_personas() , list the available expert personas.
Example
"Convene a Perspect panel on whether we should raise prices, then summarize
where the experts disagree."
Docs: https://www.tryperspect.com/docs
Nothing above is checked by us. What we check is on the safety report.
Perspect: common questions
- Is Perspect MCP server safe?
- Mostly: it is graded B (80/100). Read the Perspect safety report
- How do I install Perspect?
- It runs remotely at perspect-ai-backend.onrender.com. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
- Does Perspect need an API key?
- Yes. The registry entry asks for
X-API-Key. - Is Perspect maintained?
- The last commit was 59 days ago (2026-09-07). The latest release is v1.0.0.
- Is Perspect up?
- 100% of our last 28 checks got an answer. We check remote servers about four times a day.
- How does Perspect compare with other MCP servers?
- safety score 80/100 (higher than 60% of 48,243 servers); tools 2 (the typical server has 7); tools that change things 50% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.