catchintent MCP server
com.catchintent/catchintentcatchintent.comstreamable-httpv2.0.0Scanned
The intent layer for B2B outbound. Find, triage, and act on warmth-scored leads.
14 tools: 1 can delete or cancel things, 1 do something that can't be undone, 7 change things and 5 only read.
- Reads private data · 0
- Reads text others write · 0
- Can send data out · 0
- No findings
Tools listed without sign-in. Remote posture
With Anlyon
1 tool here can delete or cancel things and 1 does something that can't be undone. 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 catchintent MCP server can do
The catchintent MCP server is published by catchintent.com, a domain the MCP Registry verified. It has 14 tools. It can delete or cancel things (1 tool: product_delete), do things that cannot be undone, such as sending, paying or publishing (lead_update_status) and create or change data (7 tools: lead_regenerate_sequence, lead_update_sequence, lead_enrich, lead_push_to_crm and 3 more). 5 tools only read.
None of its tools reads private data, brings in text other people write, or sends data out.
None of the fixed checks matched anything in its tool definitions. That is not a safety guarantee.
Its remote endpoint lists its tools without sign-in.
Last scanned Nov 12, 2026, version 2.0.0.
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.
14 tools
Deletes or cancels 1Claude Code: deny
product_deleteDelete a product.No findings
Why it is in this group
- The name "product_delete" says "delete": a word for removing or ending something.
Description, as the server wrote it Delete a product. Fails only if it's the workspace's only product. Its audience and leads cascade-delete.
Can't be undone 1Claude Code: ask
lead_update_statusMove a lead through the triage funnel.No findings
Why it is in this group
- The name "lead_update_status" says "update": a word for a change.
- The description says "irreversible".
Description, as the server wrote it Move a lead through the triage funnel. Valid transitions: NEW → SEEN/SAVED/PUSHED/ARCHIVED, SEEN ↔ SAVED, SAVED → PUSHED/ARCHIVED, PUSHED → ARCHIVED, ARCHIVED → SEEN. PUSHED is irreversible — it marks handoff to an outreach tool / CRM.
Changes things 7Claude Code: ask
lead_enrichTrigger full LinkedIn profile enrichment via Apify (~$0.002, idempotent).No findings
Why it is in this group
- The description's first verb is "trigger": a word for a change.
Description, as the server wrote it Trigger full LinkedIn profile enrichment via Apify (~$0.002, idempotent).
lead_push_to_crmPush leads to your connected CRM (HubSpot, Close, Pipedrive, Zoho).No findings
Why it is in this group
- The name "lead_push_to_crm" says "push": a word for a change.
Description, as the server wrote it Push leads to your connected CRM (HubSpot, Close, Pipedrive, Zoho). Each lead becomes a contact / deal in the destination. Lead status does not change automatically — call lead_update_status to mark as `pushed` once CRM confirms.
lead_regenerate_sequenceRe-draft the lead's AI outreach sequence (LinkedIn/X steps).No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Re-draft the lead's AI outreach sequence (LinkedIn/X steps). Optional instructions steer the rewrite. Capped per lead — edit directly once the cap is hit.
lead_update_sequenceReplace the lead's outreach sequence steps with edited versions (marks the sequence as edited).No findings
Why it is in this group
- The name "lead_update_sequence" says "update": a word for a change.
Description, as the server wrote it Replace the lead's outreach sequence steps with edited versions (marks the sequence as edited).
product_createCreate a new product.No findings
Why it is in this group
- The name "product_create" says "create": a word for a change.
Description, as the server wrote it Create a new product. You can set sell (name/description/keywords/competitors), the structured offer, voice, and reach (roles/seniority/functions). Company firmographics (industries/size/country) are set in the dashboard, not here. Brand fields are optional and can be filled later via product_update.
product_updateUpdate a product.No findings
Why it is in this group
- The name "product_update" says "update": a word for a change.
Description, as the server wrote it Update a product. Partial — only provided fields change. You can set sell (name/description/keywords/competitors), the structured offer, voice, and reach (roles/seniority/functions). Company firmographics (industries/size/country) are set in the dashboard, not here. Reach labels are resolved strictly to canonical IDs; unknown values rejected.
workspace_usageCurrent workspace usage vs plan limits: leads delivered this billing period, team members, products, AI compute budget, daily/monthly caps.No findings
Why it is in this group
- Nothing in its name or description says what it does, so it is counted as a write.
Description, as the server wrote it Current workspace usage vs plan limits: leads delivered this billing period, team members, products, AI compute budget, daily/monthly caps.
Only reads 5Show 5 read-only tools
lead_getGet full details of one lead: profile, discovery context (fit reason, pain hypothesis, role signals, disqualifiers), the AI-drafted outreach sequence (lead.outreach), warmth score,…No findings
Why it is in this group
- The name "lead_get" says "get": a word for reading.
Description, as the server wrote it Get full details of one lead: profile, discovery context (fit reason, pain hypothesis, role signals, disqualifiers), the AI-drafted outreach sequence (lead.outreach), warmth score, and status.
lead_searchSearch leads in the workspace.No findings
Why it is in this group
- The name "lead_search" says "search": a word for reading.
Description, as the server wrote it Search leads in the workspace. A lead is always a person discovered on LinkedIn. Filter by warmth, status, or text.
product_getResolved brand profile for a product, returned as nested sections with human-readable labels: sell (name/description/keywords/competitors/offer), fit (company firmographics), reach…No findings
Why it is in this group
- The name "product_get" says "get": a word for reading.
Description, as the server wrote it Resolved brand profile for a product, returned as nested sections with human-readable labels: sell (name/description/keywords/competitors/offer), fit (company firmographics), reach (roles/seniority/functions), plus offer, voice, and domain. Drives all AI scoring + outreach drafting for that product.
product_listList every product/brand tracked by this workspace.No findings
Why it is in this group
- The name "product_list" says "list": a word for reading.
Description, as the server wrote it List every product/brand tracked by this workspace. Each product has its own brand profile, audience, and leads. Returns id, name, and timestamps.
workspace_icp_optionsGet the valid Seniority Level and Job Function labels for product targeting (the reach dimensions MCP can set; roles are free text).No findings
Why it is in this group
- The description's first verb is "get": a word for reading.
Description, as the server wrote it Get the valid Seniority Level and Job Function labels for product targeting (the reach dimensions MCP can set; roles are free text). Call this before product_update — unknown labels are rejected, never silently dropped.
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 or untrusted-input or outbound.
- Reads private data0
- Reads files, mail, messages, databases, secrets, calendars or repositories.
- Reads text others write0
- Brings in text someone else can write: web pages, inbound email, messages, issues and comments.
- Can send data out0
- 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 20, 2026, 18:35 UTC, unchanged since Oct 22, 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
- 9
- Protocol version
- 2025-06-18
- WWW-Authenticate on 401
- not observed
- resource_metadata in WWW-Authenticate
- not observed
- RFC 9728 protected resource metadata
- https://engine.catchintent.com/.well-known/oauth-protected-resource/mcp
- Authorization servers
- https://engine.catchintent.com
- Legacy HTTP+SSE transport
- no
- Dynamic client registration
- yes
- Client ID metadata documents
- no
- HighThe whole server
The endpoint served tools/list without credentials, and the list has 9 tools that change things (1 destructive, 1 irreversible, 7 write). Whether a call also works without credentials was not tested: tools are never called.
What this check looks forMatched text
https://engine.catchintent.com/mcp: tools/list returned 14 tools to an anonymous client, including product_delete (destructive), lead_update_status (irreversible), lead_regenerate_sequence (write), lead_update_sequence (write), lead_enrich (write) and 4 more
Findings
Matches of fixed checks, with the text they matched.
No check matched anything in these tool definitions. That is not a safety guarantee.
History
Changes to its tool definitions and to its remote endpoint, newest first.
No change seen yet. Its tools are rescanned every day, and a remote endpoint is looked at once a week.
Install
Pinned to version 2.0.0. Values in angle brackets are yours to fill in.
claude mcp add --transport http catchintent https://engine.catchintent.com/mcpclaude mcp add --transport http catchintent https://engine.catchintent.com/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__catchintent__lead_search",
"mcp__catchintent__lead_get",
"mcp__catchintent__workspace_icp_options",
"mcp__catchintent__product_list",
"mcp__catchintent__product_get"
],
"ask": [
"mcp__catchintent__lead_update_status",
"mcp__catchintent__lead_regenerate_sequence",
"mcp__catchintent__lead_update_sequence",
"mcp__catchintent__lead_enrich",
"mcp__catchintent__lead_push_to_crm",
"mcp__catchintent__workspace_usage",
"mcp__catchintent__product_create",
"mcp__catchintent__product_update"
],
"deny": [
"mcp__catchintent__product_delete"
]
}
}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 catchintent. Review it before you use it.
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/com.catchintent/catchintent/verify?hash=cb00d573752f4e35816a34a3d4f96ff2e820e01c36649d342b89614e0403b352" | jq -e '.changed == false'Pinned hash cb00d573752f, from Nov 12, 2026, 20:18 UTC.
Watch
Get told when its tools change: a new tool, a new description, a new class.
https://radar.anlyon.com/servers/com.catchintent/catchintent/changes.xmlAn Atom feed. Works in any feed reader or Slack's RSS app.
Badge
[](https://radar.anlyon.com/servers/com.catchintent/catchintent)Source: MCP Registry. Synced Oct 21, 2026, 17:52 UTC.
catchintent MCP server: questions and answers
Answered from the scan above, not from the publisher's description.
Is the catchintent MCP server safe?
- No scan can promise that. What its definitions show: 14 tools, 9 of which can change, send or delete something, and 0 findings from fixed checks. Allow the reads, ask before each change, and deny the deletes; the permissions block on this page does that.
Can the catchintent MCP server delete data?
- Yes. 1 tool can delete, cancel or revoke something: product_delete.
Can the catchintent MCP server do things that cannot be undone?
- Yes. 1 tool can send, pay, publish or merge: lead_update_status.
What tools does the catchintent MCP server have?
- 14 tools: 1 destructive, 1 irreversible, 7 write, 5 read. product_delete, lead_update_status, lead_regenerate_sequence, lead_update_sequence, lead_enrich, lead_push_to_crm, workspace_usage, product_create and 6 more.
Does the catchintent MCP server need sign-in or OAuth?
- Its remote endpoint listed its tools to an anonymous client, without sign-in.
Does the catchintent MCP server send data to outside services?
- None of its tools sends, posts or publishes, or takes a recipient, channel or URL.
Has the catchintent MCP server changed its tools?
- Not since Anlyon Radar started tracking it. Last scanned Nov 12, 2026.