Skip to content
verify mcp Beta VerifyMCP is currently in beta. If you notice any issues, get in touch and we’ll put it right.

YouSpot

REMOTE · YOUSPOT.COM · SCANNED SEP 20

Query one person's second brain: contacts, companies, notes, files and connected accounts.

Available components

+3 this week 84 Trust /100
Trust breakdown (7 categories)

How this component scores in each security and reliability category. Every signal is checked automatically against the live server, and we only credit what we can confirm. How we score → Why this is hard to score →

Endpoint Security94
Transport & Reachability100
Schema Quality & AI Usability81
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 19417 tokens (~178/item across 109 items; 106 tools + 3 resources), over budget; trim descriptions and params. See how to fix → Fail
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management50
  • Stability observed for 15 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage96
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 89% of tool parameters carry a description.Partial
Tool Safety75
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • 0 of 8 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation; "send_email" implies "send" and declares no destructiveHint at all, which the MCP spec reads as destructive by default. See how to fix → Fail
  • An AI judge read all 108 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities73
  • Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
  • Supports UI / widget rendering.Pass
Install

How do I install the YouSpot MCP server?

YouSpot is a hosted endpoint at https://youspot.com/mcp/v1, so there is nothing to install locally. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

remote · youspot.com

# add to Claude Code
claude mcp add --transport http com-youspot-youspot 'https://youspot.com/mcp/v1'
// .cursor/mcp.json
{
  "mcpServers": {
    "com-youspot-youspot": {
      "url": "https://youspot.com/mcp/v1"
    }
  }
}
// .vscode/mcp.json
{
  "servers": {
    "com-youspot-youspot": {
      "type": "http",
      "url": "https://youspot.com/mcp/v1"
    }
  }
}
# ~/.codex/config.toml
[mcp_servers.com-youspot-youspot]
url = "https://youspot.com/mcp/v1"
// opencode.json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "com-youspot-youspot": {
      "type": "remote",
      "url": "https://youspot.com/mcp/v1",
      "enabled": true
    }
  }
}
# add to OpenClaw
openclaw mcp add com-youspot-youspot --url 'https://youspot.com/mcp/v1' --transport streamable-http
# ~/.hermes/config.yaml
mcp_servers:
  com-youspot-youspot:
    url: "https://youspot.com/mcp/v1"
// ~/.netclaw/config/netclaw.json
{
  "McpServers": {
    "com-youspot-youspot": {
      "Transport": "http",
      "Url": "https://youspot.com/mcp/v1"
    }
  }
}
# add to Vellum
assistant mcp add com-youspot-youspot -t streamable-http -u 'https://youspot.com/mcp/v1'
// mcp.json
{
  "mcpServers": {
    "com-youspot-youspot": {
      "type": "http",
      "url": "https://youspot.com/mcp/v1"
    }
  }
}

The mcpServers block is a cross-client convention. Remote transports vary, so check your client's docs.

Changelog

Every change we have recorded for this component, newest first. Security-relevant changes are always shown. ▲ marks a change for the better, ▼ a change for the worse; unmarked changes are neutral.

  • 20 Sept 26 0
    • Tool “list_graph_objects” rewrote its description, which is the text the model reads security
    • Tool “merge_graph_objects” rewrote its description, which is the text the model reads security
    • New tool “audit_brain” functional
    • New tool “draft_cloud_agent” functional
    • New tool “unmerge_graph_objects” functional
    • “list_graph_objects” added an optional parameter “offset” cosmetic
    • “merge_graph_objects” added an optional parameter “preview” cosmetic
    • “query_graph_objects” reworded the description of “source” cosmetic
  • 19 Sept 26 +1
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “extract_brand_kit” rewrote its description, which is the text the model reads security
    • Tool “get_brand_kit” rewrote its description, which is the text the model reads security
    • Tool “read_artifact” rewrote its description, which is the text the model reads security
  • 18 Sept 26 0
    • Tool “archive_gmail_message” rewrote its description, which is the text the model reads security
    • Tool “create_gmail_draft” rewrote its description, which is the text the model reads security
    • Tool “get_calendar_events” rewrote its description, which is the text the model reads security
    • Tool “list_gmail_labels” rewrote its description, which is the text the model reads security
    • Tool “list_google_calendars” rewrote its description, which is the text the model reads security
    • Tool “search_gmail_messages” rewrote its description, which is the text the model reads security
    • Tool “update_calendar_event” rewrote its description, which is the text the model reads security
    • New resource “artifact” functional
    • New resource “brand-kits” functional
    • New tool “check_page_changes” functional
    • New tool “check_person_changes” functional
    • New tool “generate_markdown” functional
    • New tool “get_domain_keywords” functional
    • New tool “read_artifact” functional
    • New tool “share_artifact” functional
    • “get_calendar_events” reworded the description of “calendar_id” cosmetic
    • “get_calendar_events” reworded the description of “count_only” cosmetic
  • 17 Sept 26 +1
    • A breaking change shipped without a version bump: still 1.0.0 security
    • Tool “changelog_save_draft” was removed security
    • Tool “changelog_sources” was removed security
    • Tool “get_substack_post_stats” was removed security
    • Tool “get_substack_posts” was removed security
    • Tool “get_substack_subscriber_counts” was removed security
    • Tool “get_substack_subscribers” was removed security
    • Tool “import_substack_subscribers” was removed security
    • Tool “intake_get_email” was removed security
    • Tool “intake_record_decision” was removed security
    • Tool “intake_reply” was removed security
    • Tool “linear_comment_on_issue” was removed security
    • Tool “linear_create_issue” was removed security
    • Tool “linear_get_issue” was removed security
    • Tool “linear_relate_issues” was removed security
    • Tool “linear_routing_catalog” was removed security
    • Tool “linear_search_issues” was removed security
    • Tool “lookup_substack_subscriber” was removed security
    • Tool “generate_email” rewrote its description, which is the text the model reads security
    • Tool “generate_og_image” rewrote its description, which is the text the model reads security
    • Tool “generate_pdf” rewrote its description, which is the text the model reads security
    • Tool “get_artifact” rewrote its description, which is the text the model reads security
    • Tool “get_calendar_events” rewrote its description, which is the text the model reads security
    • Tool “get_my_bookmarks” rewrote its description, which is the text the model reads security
    • Tool “get_my_tweets” rewrote its description, which is the text the model reads security
    • Tool “get_slack_thread” rewrote its description, which is the text the model reads security
    • Tool “get_twitter_following” rewrote its description, which is the text the model reads security
    • Tool “get_twitter_profile” rewrote its description, which is the text the model reads security
    • Tool “list_artifacts” rewrote its description, which is the text the model reads security
    • Tool “list_google_calendars” rewrote its description, which is the text the model reads security
    • Tool “plan_generation” rewrote its description, which is the text the model reads security
    • Tool “save_as_template” rewrote its description, which is the text the model reads security
    • Tool “search_gmail_messages” rewrote its description, which is the text the model reads security
    • Tool “search_slack_messages” rewrote its description, which is the text the model reads security
    • Tool “search_tweets” rewrote its description, which is the text the model reads security
    • Tool “send_text_to_user” rewrote its description, which is the text the model reads security
    • Tool coverage: 82% → 88% functional
    • New tool “cancel_scheduled_text” functional
    • New tool “list_scheduled_texts” functional
    • “generate_og_image” added an optional parameter “size” cosmetic
    • “plan_generation” added an optional parameter “size” cosmetic
    • “send_text_to_user” added an optional parameter “send_at” cosmetic
    • Tool “generate_og_image” changed its title: Generate social image → Generate image cosmetic
  • 16 Sept 26 0
    • A breaking change shipped without a version bump: still 1.0.0 security
    • Tool “linear_completed_issues” was removed security
    • Tool “changelog_save_draft” rewrote its description, which is the text the model reads security
    • “changelog_save_draft” added a required parameter “day”, so existing callers break functional
    • “changelog_save_draft” added a required parameter “items”, so existing callers break functional
    • “changelog_save_draft” dropped the required parameter “sources” functional
    • “changelog_save_draft” dropped the required parameter “week_start” functional
    • New tool “changelog_sources” functional
    • New tool “generate_substack_post” functional
    • New tool “get_my_plan” functional
    • New tool “get_substack_post_stats” functional
    • New tool “get_substack_posts” functional
    • New tool “get_substack_subscriber_counts” functional
    • New tool “get_substack_subscribers” functional
    • New tool “import_substack_subscribers” functional
    • New tool “lookup_substack_subscriber” functional
  • 15 Sept 26 +1
    • Tool “draft_email_in_gmail” rewrote its description, which is the text the model reads security
    • Tool “generate_email” rewrote its description, which is the text the model reads security
    • Schema quality: 15809 → 17554 functional
    • New tool “create_brand_kit” functional
    • New tool “extract_brand_kit” functional
    • New tool “generate_pdf” functional
    • New tool “get_artifact” functional
    • New tool “get_brand_kit” functional
    • New tool “list_artifacts” functional
    • New tool “list_templates” functional
    • New tool “plan_generation” functional
    • New tool “save_as_template” functional
    • New tool “set_default_brand_kit” functional
    • New tool “update_brand_kit” functional
    • “generate_email” added an optional parameter “saved_template_id” cosmetic
    • “generate_og_image” added an optional parameter “saved_template_id” cosmetic
    • “generate_email” made “subject” optional cosmetic
    • “generate_og_image” made “props” optional cosmetic
  • 14 Sept 26 0
    • New tool “draft_email_in_gmail” functional
    • New tool “generate_email” functional
    • New tool “generate_og_image” functional
    • New tool “list_brand_kits” functional
  • 13 Sept 26 0
    • Tool “create_calendar_event” rewrote its description, which is the text the model reads security
    • “create_calendar_event” added an optional parameter “action_id” cosmetic
    • “create_calendar_event” added an optional parameter “all_day” cosmetic
    • “create_calendar_event” added an optional parameter “timezone” cosmetic
    • “create_calendar_event” reworded the description of “account” cosmetic
    • “create_calendar_event” reworded the description of “calendar_id” cosmetic
    • “create_calendar_event” reworded the description of “description” cosmetic
    • “create_calendar_event” reworded the description of “end” cosmetic
    • “create_calendar_event” reworded the description of “location” cosmetic
    • “create_calendar_event” reworded the description of “start” cosmetic
    • “create_calendar_event” reworded the description of “summary” cosmetic
    • “create_calendar_event” made “end” optional cosmetic
    • “create_calendar_event” made “start” optional cosmetic
    • “create_calendar_event” made “summary” optional cosmetic
    • Tool “create_calendar_event” changed its title: Create calendar event → Add event to calendar cosmetic
Diagnostics

Diagnostic detail from the automated scan of this channel: what the scanner observed at each step, so you can see exactly where a check passed or failed. It is informational only and never changes the trust score.

Captured 20 Sept 2026 · Probed https://youspot.com/mcp/v1

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=youspot.com CN=WE1,O=Google Trust Services,C=US 15 Aug 2026 13 Nov 2026 ECDSA 256 ECDSA-SHA256 9a1e13268e4b1f610eb83d6e63fa2638
SANs: youspot.com, *.youspot.com
CN=WE1,O=Google Trust Services,C=US (CA) CN=GTS Root R4,O=Google Trust Services LLC,C=US 13 Dec 2023 20 Feb 2029 ECDSA 256 ECDSA-SHA384 7ff31977972c224a76155d13b6d685e3
CN=GTS Root R4,O=Google Trust Services LLC,C=US (CA) CN=GlobalSign Root CA,OU=Root CA,O=GlobalSign nv-sa,C=BE 15 Nov 2023 28 Jan 2028 ECDSA 384 SHA256-RSA 7fe530bf331343bedd821610493d8a1b

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of youspot.com. Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
com. present 19718 13 Verified
youspot.com. absent Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication Enforced and verified

The endpoint asked for a token and published valid RFC 9728 metadata describing how to get one.

Result Enforced and verified
Enforced On tool calls
HTTP status 200

WWW-Authenticate challenge Bearer resource_metadata="https://youspot.com/.well-known/oauth-protected-resource/mcp/v1", error="invalid_token"

Bearer resource_metadata="https://youspot.com/.well-known/oauth-protected-resource/mcp/v1", error="invalid_token"
Header Value
strict-transport-security max-age=63072000; includeSubDomains; preload
x-content-type-options nosniff
x-frame-options DENY
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Protected resource metadata

Document https://youspot.com/.well-known/oauth-protected-resource/mcp/v1
Retrieved Yes
Resource https://youspot.com/mcp/v1
Authorisation server https://youspot.com

Background: How OAuth 2.1 works in the 2026 MCP spec →

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://youspot.com/mcp/v1 Verified 200
http (plaintext) http://youspot.com/mcp/v1 HTTPS enforced 308 https://youspot.com/mcp/v1
MCP tools · 106 exposed · ~19,132 tokens

The tools this component advertises to a client, with an estimated token cost for each. Expand a tool to see its parameters and schema. The per-tool counts are indicative and are not scored directly; the schema's total context footprint is one signal in Schema Quality & AI Usability. A tool's description is untrusted text the model reads on every call, which is what makes this list a security surface and not just an inventory: how tool poisoning works →

Tool Tokens
unmerge_graph_objects ~120

Undo a merge_graph_objects call: the record that was folded in comes back, its connections move off the kept record, the duplicate edges that were dropped are recreated, and the fields it contributed are removed from the kept record. Only fields the merge itself copied over, and only while they still hold what the merge put there, so a later edit survives. keep_id is the record that survived the merge.

NameTypeReqDescription
keep_idstringyesThe record that survived the merge.
merged_idstringyesThe record that was folded into it.

No output schema declared.

No examples provided.

update_brand_kit ~179

Change fields on a brand kit; fields left out keep their value. Set review_state 'confirmed' only after the user has looked at an imported kit and approved it. Returns the updated kit.

NameTypeReqDescription
brand_kit_idstringyesA brand_kit_id from list_brand_kits.
colorsobjectHex colors (#rrggbb). Any left out keep their current value.
dark_modestring
documentsobjectHow this brand lays out PDFs. Any left out use the default.
domainstringThe brand website host, like acme.com.
fontsobject
namestringThe brand name.
radiusstringCorner radius in px, rem or em, like 8px.
review_statestring

No output schema declared.

No examples provided.

update_calendar_event ~241

Update one Google Calendar event: change its title (summary), description, location, or start/end times. Only the fields you pass change; everything else stays. Get the event's id (and its calendar_id, if it isn't on the primary calendar) from get_calendar_events first. Use only when the user asked for the change; edits land on their real calendar immediately, and other attendees can see them. start/end are RFC3339 timestamps ('2026-08-25T19:00:00-04:00').

NameTypeReqDescription
accountstringEmail address of the connected Google account holding the event. Omit to use the account with calendar access.
calendar_idstringThe calendar holding the event (from list_google_calendars). Omit for primary.
descriptionstringNew description.
endstringNew end, RFC3339 dateTime.
event_idstringyesThe event id from get_calendar_events.
locationstringNew location.
startstringNew start, RFC3339 dateTime.
summarystringNew event title.

No output schema declared.

No examples provided.

update_my_profile ~185

Update the user's own profile fields when they ask: timezone, name, headline, company website, LinkedIn URL or X handle. Only pass the fields they asked to change. timezone must be an IANA zone name — translate their words yourself ('ET', 'eastern time', 'Boston time' all mean America/New_York; 'PST' means America/Los_Angeles). Confirm what was set in your reply.

NameTypeReqDescription
first_namestring
headlinestringThe one-liner under their name.
last_namestring
linkedin_profile_urlstring
timezonestringIANA zone name, e.g. 'America/New_York'. Empty string clears it.
twitter_usernamestring
websitestringTheir company's domain, e.g. 'acme.com'.

No output schema declared.

No examples provided.

web_search ~181

Search the open web and get back titles, URLs and snippets. Use when the answer is not in the user's own data and not about one named company: what a competitor is saying publicly, what is happening in a market, whether a claim checks out. For one company in depth use research_company; for the contents of a page you already have a URL for use read_web_page. Results are links and snippets, not the pages themselves.

NameTypeReqDescription
domainstringRestrict to one site, e.g. 'techcrunch.com'. Omit to search everywhere.
max_resultsintegerHow many results (default 5, max 10).
querystringyesWhat to search for, in plain words.
since_daysintegerOnly results from the last N days. Use for "what happened recently" questions.

No output schema declared.

No examples provided.

what_needs_attention ~214

What this user should deal with right now, computed from their sent mail, their calendar and their LinkedIn export: people who went quiet after real correspondence, people they are meeting this week, who they write to most, invitations nobody answered, and the shape of their network. Each item carries the reason and where the numbers came from. Call this for 'what needs my attention', 'who am I forgetting', 'who should I follow up with', 'what should I do today' and anything else that asks who to deal with without naming one person. Then show an attention_list card and never write the items out yourself. `readiness` says whether the mailbox has finished being read: when it is 'pending' or 'partial', say so rather than presenting a short list as the whole picture.

NameTypeReqDescription
kindsarrayRestrict to certain kinds. Omit for everything, which is almost always right.
limitintegerHow many items to return (default 5, max 25).

No output schema declared.

No examples provided.

Common questions

What is the YouSpot MCP server?

YouSpot is an MCP server listed in the public MCP registry as com.youspot/youspot. Query one person's second brain: contacts, companies, notes, files and connected accounts. This page covers its hosted endpoint (https://youspot.com/mcp/v1).

Is the YouSpot MCP server safe to use?

YouSpot scores 84 out of 100 on VerifyMCP. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

What tools does the YouSpot MCP server expose?

YouSpot exposes 106 tools: what_needs_attention, get_my_plan, draft_cloud_agent, research_company, company_signals, and 101 more. Their descriptions and schemas cost roughly 19,132 tokens of context every time the server is loaded.

Does the YouSpot MCP server require authentication?

Yes. YouSpot asked us for credentials when we connected, so you will need to authorise it in your MCP client before it can do anything.

Is the YouSpot MCP server still maintained?

YouSpot is still listed as active in the MCP registry. We last reached this channel on 20 September 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.