Metacpan as tools for your agent. Unofficial: not affiliated with or endorsed by metacpan.org. Unbrowse compiled these from metacpan.org's own requests: each call replays the site's first-party API server-side and returns a verified result. No scraping of rendered pages, no browser on your side, no metacpan.org API key.
Connect the metacpan.org MCP
This server is a tool scope holding only metacpan.org: its compiled tools plus the Unbrowse tools that run them, so the agent's tool list stays small and every call stays on metacpan.org.
claude mcp add --transport http metacpan https://unbrowse.ai/mcp/metacpan.org
codex mcp add metacpan --url https://unbrowse.ai/mcp/metacpan.org && codex mcp login metacpan
{"mcpServers":{"metacpan":{"url":"https://unbrowse.ai/mcp/metacpan.org"}}}
The first connect signs in to Unbrowse with OAuth (free tier, only verified results count). For scripts, send Authorization: Bearer $UNBROWSE_API_KEY (key from https://unbrowse.ai/app/keys; keep it in a secret manager, never in config you commit).
If none of the tools below are in this session's tool list, the server is not connected or not signed in: say so and stop. Do not fetch metacpan.org some other way and present it as this skill's result.
Tools
metacpan_org__get_search — Search metacpan
Search metacpan. Inputs: query. Returns the page's title, readable text and links. Read-only on metacpan.org.
query(string, required) — query (typed during “fill Search the CPAN”)size(integer) — optional, e.g. "20"select(array) — Keep only these parts of the result: dots walk keys, [] maps over a list, a final {a,b} keeps several keys (e.g. "results[].{title,url}"). Unmatched paths come back in selectMissing.
{"query":"<query>"}
Always there too: unbrowse.run (a task on metacpan.org in plain words), unbrowse.inspect, unbrowse.resume, unbrowse.scrape and unbrowse.map (any page on metacpan.org), and the recorded cloud browser unbrowse.browse.open → unbrowse.browse.act → unbrowse.browse.finish. Hosts that reject dotted names show them with _ (unbrowse_run).
How to call
- Pick the tool whose title matches the job and pass its inputs. Leave the site's recorded parameters out unless the user asked for something they control.
- Read
status.succeededcarries the verifiedresult.input_requiredis not a failure: answer the open fields withunbrowse.resume {runId, answers}on the same run. - No tool fits:
unbrowse.run {task}. It fails withno_capabilitywhen nothing is compiled for that yet: do it once withunbrowse.browse.openon metacpan.org →unbrowse.browse.act→unbrowse.browse.finish, which compiles a new tool this server lists next time. Anything off metacpan.org is refused here (not_in_scope): use the general Unbrowse server for that. - Signing in: never ask the user for a password.
unbrowse.browse.actwithaction: "autofill"fills metacpan.org's login from their Unbrowse password manager. - Report only what a
succeededresult says.outcome_unknownmeans a change may have happened: check before retrying. Posting, buying, sending or deleting needs the user's go-ahead.
Without MCP
Every tool is also a REST call:
curl -s https://unbrowse.ai/api/v1/sites/metacpan.org/call/metacpan_org__get_search \
-H "authorization: Bearer $UNBROWSE_API_KEY" -H "content-type: application/json" \
-d '{"query":"<query>"}'
OpenAPI: https://unbrowse.ai/api/v1/sites/metacpan.org/openapi.json. Every other site: the general Unbrowse skill (https://github.com/unbrowse-ai/unbrowse) and https://unbrowse.ai/mcp.