TypedPull MCP server
ai.peerfoundry/typedpullpeerfoundry.aistreamable-httpv0.1.0Scanned
Return only the schema fields you name from one public web page. No raw HTML.
5 tools: 3 change things and 2 only read.
- Reads private data · 0
- Reads text others write · 1
- Can send data out · 2
- 1 finding
Tools listed without sign-in. Remote posture
With Anlyon
3 tools here change things. Govern them.
- Anlyon lists the tools and adopts none.
- Each tool you adopt gets approvals and receipts.
- Your agent never holds the key.
A tool your agent calls directly is not routed through Anlyon and is not governed by it. Anlyon Radar only lists and labels, and these labels are the same either way.
What the TypedPull MCP server can do
The TypedPull MCP server is published by peerfoundry.ai, a domain the MCP Registry verified. It has 5 tools. It can create or change data (3 tools: extract, extract_batch and keys.create), but cannot delete data. 2 tools only read.
1 tool brings in text other people can write (extract); 2 tools can send data out of your system (extract and explain_extractor).
The fixed checks matched 1 finding (annotation-conflict). Each one comes with the text it matched.
Its remote endpoint lists its tools without sign-in, and its tools changed once since Anlyon Radar first saw them.
Last scanned Nov 13, 2026, version 0.1.0.
Tools
Grouped by what each tool does, most consequential first. Open one for its reasons and full description; descriptions are the publisher's own words.
5 tools
Changes things 3Claude Code: ask
extractReturn fields from one public page.Reads text others writeCan send data out1 finding
Why it is in this group
- The description's first verb is "return": a word for reading.
- The server marks it as not read-only (readOnlyHint: false).
What it can reach
- untrusted-inputThe input takes a URL (input.url), and the tool reads it: it reads web pages, which anyone can write.
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Findings
- Warn
The server marks "extract" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false}; The description's first verb is "return": a word for reading.
Description, as the server wrote it Return fields from one public page. Call extractors.list for hosts, paths, and the sample schema. You can ask for title, heading, or both. If the page has no extractor, the error points to extractors.list. Call keys.create once. Pass caller_key on every later tools/call.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
extract_batchRun up to 20 extract calls.No findings
Why it is in this group
- The description's first verb is "run": a word for a change.
Description, as the server wrote it Run up to 20 extract calls. Each item has its own status. Call extractors.list for the sample schema. Call keys.create once. Pass caller_key on every later tools/call.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
keys.createMint a pf_ caller key.No findings
Why it is in this group
- The name "keys.create" says "create": a word for a change.
Description, as the server wrote it Mint a pf_ caller key. The raw key is shown once. Pass this key on every later tools/call. Send it as the caller_key argument.
Annotations the server declares
- readOnlyHint: false
- destructiveHint: false
Only reads 2Show 2 read-only tools
explain_extractorShow selectors, version, and hit count.Can send data outNo findings
Why it is in this group
- The name "explain_extractor" says "explain": a word for reading.
What it can reach
- outboundThe input takes a URL (input.url): a request to a URL can carry data to whoever runs it.
Claude Code: ask, because it is tagged outbound.
Description, as the server wrote it Show selectors, version, and hit count. This does not fetch the page.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
extractors.listList active pages, fields, and a sample schema.No findings
Why it is in this group
- The name "extractors.list" says "list": a word for reading.
Description, as the server wrote it List active pages, fields, and a sample schema. This does not fetch a page. No caller key is required.
Annotations the server declares
- readOnlyHint: true
- destructiveHint: false
This is not a safety rating, and no finding is not a safety guarantee. The groups and findings come from fixed checks of the tool definitions the server returned on the date shown, not from its code or what it does when called. How the checks work.
Exfil surface
Which tools read private data, which read text someone else can write, and which can send data out. One of each is a path a prompt injection can use.
No private-data, untrusted-input, outbound path in this server alone: no tool is tagged private-data.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write1
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out2
- Can carry data to people or systems: it sends, posts or publishes, or takes a recipient, channel or URL.
Other servers in the same agent add their own tools to these paths. Audit your whole setup to see them together.
Remote posture
What anyone on the internet sees at the remote endpoint: an anonymous initialize and tools/list, and the public OAuth metadata.
Looked at Nov 15, 2026, 13:21 UTC, unchanged since Oct 31, 2026. No credentials were sent and no tool was called. What is looked at.
- Reachable
- yes
- HTTP status of an anonymous initialize
- 200
- tools/list served without credentials
- yes
- Tools that change things, listed without credentials
- 3
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- not observed
- Authorization servers
- not observed
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- not observed
- Client ID metadata documents
- not observed
- WarnThe whole server
The endpoint served tools/list without credentials, and the list has 3 tools that change things (3 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://typedpull.peerfoundry.ai/mcp: tools/list returned 5 tools to an anonymous client, including extract (write), extract_batch (write), keys.create (write)
Findings
Matches of fixed checks, with the text they matched.
- Warnextract
The server marks "extract" as not read-only (readOnlyHint: false), and its words say it reads.
What this check looks forMatched text
annotations: {"readOnlyHint":false,"destructiveHint":false}; The description's first verb is "return": a word for reading.
History
Changes to its tool definitions and to its remote endpoint, newest first.
Tools1 added, 3 changed.+1 added~3 changedView diff
- Added:extractors.listOnly reads
- Changed:extractChanges thingsdescriptioninputSchema
- Changed:extract_batchChanges thingsdescriptioninputSchema
- Changed:keys.createChanges thingsdescription
Install
Pinned to version 0.1.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http typedpull https://typedpull.peerfoundry.ai/mcpclaude mcp add --transport http typedpull https://typedpull.peerfoundry.ai/mcpRun in a terminal.
Claude Code permissions
Allow the reads, ask before a change or a way out, deny the deletes. Paste into .claude/settings.json.
{
"permissions": {
"allow": [
"mcp__typedpull__extractors_list"
],
"ask": [
"mcp__typedpull__extract",
"mcp__typedpull__extract_batch",
"mcp__typedpull__explain_extractor",
"mcp__typedpull__keys_create"
],
"deny": []
}
}Tools that only read are allowed, tools that change things ask first, tools that delete or cancel are denied. A read that can send data out (it takes a URL, say) asks first too. It assumes the server is installed as typedpull. Review it before you use it.
Capability tags behind 2 rules
- mcp__typedpull__extract untrusted-input, outbound
- mcp__typedpull__explain_extractor outbound
Pin
Keep the decision: fail CI when the tools change, follow every change, or show a badge.
Pin in CI
Fail a build when the tools you reviewed are not the tools the server serves today.
curl -s "https://radar.anlyon.com/api/v1/servers/ai.peerfoundry/typedpull/verify?hash=3b010a249baa76681f893a2b487065230364ea3a204103f49d043950d4b623d3" | jq -e '.changed == false'Pinned hash 3b010a249baa, from Nov 13, 2026, 07:17 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/ai.peerfoundry/typedpull/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/ai.peerfoundry/typedpull)Source: MCP Registry. Synced Oct 31, 2026, 11:17 UTC.
TypedPull MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the TypedPull MCP server safe?
- No scan can promise that. What its definitions show: 5 tools, 3 of which can change, send or delete something, and 1 finding from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the TypedPull MCP server delete data?
- No tool is classed as destructive: going by their definitions, none of them deletes, cancels or revokes anything.
Can the TypedPull MCP server do things that cannot be undone?
- No tool is classed as irreversible: none of them sends, pays, publishes or merges, going by their definitions.
What tools does the TypedPull MCP server have?
- 5 tools: 3 write, 2 read. extract, extract_batch, keys.create, explain_extractor and extractors.list.
Does the TypedPull MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the TypedPull MCP server send data to outside services?
- 2 tools can carry data out (it sends, posts or publishes, or takes a recipient, channel or URL): extract and explain_extractor.
Has the TypedPull MCP server changed its tools?
- Yes, once since Anlyon Radar started tracking it, most recently on Nov 13, 2026. Every change is on this page and in its Atom feed.