Perigon for AI agents
Perigon is a news and web content API that returns structured data on articles, journalists, and media sources. Media monitoring and research teams use it to track coverage on topics and companies. Connect it once through Arc0, and your agent, or Claude, ChatGPT and Cursor, can use it through one MCP endpoint, limited to what each user approved.
What agents do in Perigon.
Search news articles on a topic
Pull recent news articles mentioning a company or topic for a monitoring report.
Check a journalist's coverage
Look up a journalist's recent articles read-only before pitching a story.
Search Wikipedia for background
Run a vector search against Wikipedia articles to add background context to a brief.
9 Perigon actions, graded by risk.
Every Perigon action is tagged read, write or destructive, so one policy covers the whole app and new actions inherit the right default.
read
7Look things up. Allowed by default.
- perigon.get_topicsGet Topics
- perigon.get_sourcesGet Media Sources
- perigon.get_storiesGet Stories
- perigon.get_articlesGet News Articles
- perigon.get_companiesGet Companies
- perigon.get_wikipediaGet Wikipedia Articles
- perigon.get_journalistsGet Journalists
write
2Create and change things. Allow, or ask the user first.
- perigon.vector_search_articlesVector Search Articles
- perigon.vector_search_wikipediaVector Search Wikipedia
destructive
0Delete, cancel or archive. Ask first, or deny outright.
- No destructive actions.
Perigon in three steps.
- 01Your users connect PerigonThey add their Perigon api key on Arc0 Connect, under your brand. It goes straight into the vault.
- 02You set the rulesReads run, and writes like “vector Search Articles” can wait for the user to approve.
- 03Any agent can actYour agent calls Perigon through the Arc0 SDK or MCP, and so can Claude, ChatGPT and Cursor. Every call lands on the audit log.
await arc0.policies.set('perigon', { read: 'allow', write: 'ask', // vector_search_articles destructive: 'deny', }) # Claude Code: the same connection, one URL $ claude mcp add --transport http arc0 \ https://mcp.arc0.ai/u/u_8f2
How Perigon connects.
Users add their Perigon api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
The same Perigon connection serves your agent over MCP and your own backend over REST and the proxy, so a user connects once. How Arc0 handles credentials →
- AUTH
- API key
- CREDENTIALS
- Per-tenant encrypted vault
- MODEL SEES
- Results only, never credentials
- AUDIT LOG
- Every call, on every plan
Use Perigon from any agent.
ClaudeChatGPTCursor
Codex
VS CodeOpenAI Agents SDKClaude Agent SDK
Vercel AI SDK
Mastra
LangGraph
Perigon and Arc0, answered.
Can I use Perigon with Claude, ChatGPT or Cursor?
Yes. Connect Perigon to Arc0 once, then add your Arc0 MCP URL to Claude, ChatGPT, Cursor, Claude Code or any other remote-MCP client. Each assistant only gets the Perigon actions you allow.
How do users connect Perigon?
Users add their Perigon api key on Arc0 Connect. It is encrypted in the vault, never shown to the model, and each user can rotate or revoke it at any time.
Which Perigon actions can my agent take?
9 in total: 7 read, 2 write and 0 destructive, such as “vector Search Articles”. Your policies decide which of them each agent may call.
Can I make my agent read-only in Perigon?
Yes. Allow read actions and deny writes in the Perigon policy. Your agent can still look things up, and any write it attempts is blocked and logged.
Can my own backend call Perigon too?
Yes. The same Perigon connection is available over REST and through the Arc0 proxy, so your product and your agent share one connection per user.
Plug Perigon into your agent.
Your users connect Perigon once, under your brand. Your agent gets 9 actions behind your policies, with every call on the record.
Free to build · MCP + REST · Audit log on every plan