PHION Evidence Engine
not read yet
Use
- For
- AI agents and developers who need signed, verifiable evidence from public web sources
- Runs as
- API
- Used for
- fetch a public web source and screen it for prompt injection
- hash normalized observations and issue ed25519 signed receipts
- verify evidence receipts offline without network access
- Has an MCP server (1 in the registry)public registry →
- Publishes llms.txt, a file written for AI assistantsphion.systems ↗
- MCP serversystems.phion/evidence-engineverified in the MCP registry
- Stateanswers, 1 toolschecked 2026-10-26
- Address to connectphion.systems/mcp/task
- OpenAPI spec175 pathsthe spec ↗
This card as JSON, for your agent →
Each line is something a program found when it went looking: the registry entry, the server's own answer, a spec that parses. A missing line means we did not find it, not that it does not exist.
Figure and bar: visits/mo, estimate · year: online since
- #1
Genspark
Runs an agent that researches a topic and produces slides, spreadsheets, documents and web pages from a text prompt, inside one chat workspace.
227k - #2
Pickaxe
Builds branded chatbots and agents on language models without code, with memberships and payments for selling access to them.
26.7kActiveFrom $37/mo - #3
BrowserlessMCP · sign-in
Hosts managed headless Chrome browsers that scripts and AI agents drive over Puppeteer or Playwright connections, with stealth, proxies and captcha handling.
13.9kActiveFrom $25/mo - #4
You.com
Returns live web search results and cleaned page content through APIs that AI agents and LLM apps call for grounding.
13.6k2020 - #5
SpeakeasyMCP · sign-in
Routes agent traffic through one identity-checked MCP gateway, enforcing security policy on every prompt and tool call.
5.8kActiveFrom $0.35 per use2021 - #6
Twin
Builds autonomous agents that run business processes like lead generation, content creation, and outreach in Slack and email.
2.5kActiveFrom $29/mo2024
Not it? Say what you need
betaThree tools from the Atlas for the job you describe, each with what fits and what does not.
No notes yet. What do you use PHION Evidence Engine for?
Sign in to leave a noteWhat is PHION Evidence Engine?
Fetches a public web source for AI agents, screens it for prompt injection, and returns an Ed25519-signed receipt of the observed content. It is listed in the Atlas under Agents.
Who is PHION Evidence Engine for?
AI agents and developers who need signed, verifiable evidence from public web sources
Do people use PHION Evidence Engine?
Little sign of use.
What are alternatives to PHION Evidence Engine?
In Agents, by use: Genspark, Pickaxe, Browserless, You.com, Speakeasy, Twin.
How we read a tool
No votes, no reviews, no vendor claims. Every week a crawler reads each tool's own site and a few public registries, and the words on the card are bands over what it read.
- Use: visits to the site (estimated), installs from npm and PyPI, presence in Chrome's usage report.
- Activity: the newest release on GitHub, npm or PyPI; the newest dated page on the site; open roles on a public jobs board.
- Price: the vendor's own pricing page, read with the date. A figure is printed only when it is on that page.
- The line and the use cases are written by us from the homepage, one tool at a time, and refused when they repeat the vendor's marketing.
How AI assistants read each site — the reading vendors ask us about — is on each tool's own visibility page.
How we read every tool → · By INITE Atlas Desk
Cookies
Before we count this visit
Analytics and ad measurement tell us which pages and which of our ads do their job: Google Analytics and Google Ads, the Meta pixel, Yandex Metrica, and one first-party id of our own. Nothing is stored until you answer, and declining changes nothing about the site.