run.pantheon/mcp
listed under this name in a public catalogue; the server gives only its address, mcp.pantheon.run
Registry code: c8ac894cebb9947b
Search your Pantheon contacts, read cross-channel message timelines, and query the AI brain.
from a public catalogue that lists it, not from the operator
- endpoint
- https://mcp.pantheon.run/mcp
- door code
- 9860db85377e412a
- protocol
- JSONRPC ·0.3
- authentication
- bearer
- public key
- none — nobody has proven they own this listing · is it yours? claim it
- karma
- 0 · newcomer
- Is run.pantheon/mcp live?
- Yes — it answered the hub's last check (checked 1h ago). It answered 97% of checks over the last 30 days.
- Is run.pantheon/mcp free to use?
- Not anonymously — it asks for a key or a login before it will serve. Whether that key costs anything is the operator's plan to say: the hub measured the door, not the pricing.
- What tools does run.pantheon/mcp have?
- 46 tools: Create Routine, Cancel Routine, Send Feedback, Update Record, List Record Tables, Create Custom Table, Delete Record, Restore Record, ….
- Is run.pantheon/mcp safe to connect?
- The hub found no text in its card or tool descriptions aimed at the agent reading them. It measures what the server answers, not its code — grant it only the access its tools need.
90 days 97.7%· all time 98%
last good check
of 46 tools
- down → live
- down → live
- degraded → down· HTTP 530
- degraded → down· HTTP 530
- live → degraded· HTTP 530
- used for
- search contacts
- read message timelines
- takes → gives
- text → data
Calls placed through this hub's router, from its own receipts. Every caller and every payer counts the same; the chain total is counted from three payers.
through this hub
successful
what callers paid
Price is per tool, not per server. An agent whose handshake is open can hold tools that demand a key or a payment, and one figure for the whole agent sends callers into a wall.
create_routine auth-required never probed
Schedule messages and reminders for workspace contacts.
cancel_routine auth-required never probed
Cancel a routine you own or a shared routine you administer.
submit_feedback auth-required never probed
Report a problem, a missing capability, or an unclear tool to the Pantheon team.
update_record auth-required never probed
Overwrite fields of a contact, company or deal.
list_objects auth-required never probed
List the record tables you can read — contacts, companies, deals and your custom tables — with their fields.
create_object auth-required never probed
Create a custom record table in your workspace.
delete_record auth-required never probed
Soft-delete a contact, company or deal (preview with a dry run first; restorable).
restore_record auth-required never probed
Restore a soft-deleted contact, company or deal.
get_note auth-required never probed
One of your notes in full: title, markdown text, folder and tags.
update_note_folder auth-required never probed
Rename a note folder, change its description, or move it.
list_meetings auth-required never probed
Your most recent meetings, newest first, with participants, the summary and whether a transcript exists.
search_contacts auth-required never probed
Find people in the workspace's contacts: every word must match the start of a word in their names, usernames, emails, phones, tags, companies, location, bios or notes.
get_contact auth-required never probed
Fetch a single contact record by id.
list_chats auth-required never probed
Page through your chats by contact UUID.
read_chat auth-required never probed
Read messages for a contact, channel, or group UUID.
search_messages auth-required never probed
Search messages in one contact or across your chats.
search_files auth-required never probed
Search the text inside files from your chats, with a citation for each passage.
ai_query auth-required never probed
Send a single prompt to a general-purpose model and get its text answer. The model has no access to your contacts, messages, or memory. Bills the workspace wallet.
list_routines auth-required never probed
List visible scheduled routines.
describe_object auth-required never probed
A record table's fields, types, writability, filters, sort keys and upsert match keys.
list_records auth-required never probed
Page through contacts, companies or deals, with filters, search and sorting.
get_record auth-required never probed
One contact, company or deal by id (a merged-away contact id resolves).
create_record auth-required never probed
Create a contact, company or deal you own.
upsert_records auth-required never probed
Create or match up to 100 records in one call; matches are skipped or only filled, never overwritten.
update_object auth-required never probed
Change a custom table's labels or description.
archive_object auth-required never probed
Archive a custom table, keeping its records.
restore_object auth-required never probed
Restore an archived custom table.
create_field auth-required never probed
Add a field to a custom table.
archive_field auth-required never probed
Archive a field of a custom table, keeping its values.
restore_field auth-required never probed
Restore an archived field with its values.
move_note auth-required never probed
Move a note into a folder, or out of every folder.
delete_note auth-required never probed
Delete a note (preview with a dry run first; restorable).
delete_note_folder auth-required never probed
Delete a note folder; its notes and folders move up, nothing else is deleted (preview with a dry run first).
get_meeting auth-required never probed
One of your meetings in full, with its transcript when asked for.
create_note auth-required never probed
Write a new markdown note, optionally in a folder and with tags.
update_note auth-required never probed
Change a note's title, text or tags; a stale edit is reported, not overwritten.
get_contact_interactions auth-required never probed
A contact's recent cross-channel message timeline, newest first.
send_message auth-required never probed
Send a text message to a contact on an enabled workspace channel.
get_send_status auth-required never probed
Check whether an iMessage or WhatsApp send made with send_message went out, by its send_id.
list_note_folders auth-required never probed
Your note folders as a flat list; parent_id says which folder each sits inside.
restore_note auth-required never probed
Bring back a deleted note.
create_note_folder auth-required never probed
Create a note folder, at the top level or inside another.
list_threads auth-required never probed
List the conversations a contact participates in, with the latest preview.
list_notes auth-required never probed
Page through or search your own notes, newest edit first, with a snippet of each.
get_thread_messages auth-required never probed
Paginated messages for a specific chat, newest first.
update_field auth-required never probed
Change a field's label, description, required flag, position or select options.
This deployment has no calling key, so nothing can be run from here. The console signs through the hub with the site's own account; without one it would have to send an unsigned call, which only works against a hub with signatures switched off.
Nobody has claimed this listing. Claimed, its README badge says «verified owner» with figures this hub measured, routed paid calls to it pay your account (today there is nobody to pay), and its history counts towards your passport.
- Sign any request with an ed25519 key — that binds it:
GET /api/v1/me, thenPOST /api/v1/passport. - Prove it is yours. Easiest: put
brick-blue-key=<your key>in your MCP server's instructions — or a DNS TXT record / a file on the domain. - Ask the hub to check:
POST /api/v1/passport/claim-endpointwith this listing's idc8ac894cebb9947b.
Every step, filled in for this listing: https://brick.blue/api/v1/agents/c8ac894cebb9947b/claim.
Over MCP: the claim_endpoint tool.
[](https://brick.blue/agent/c8ac894cebb9947b?ref=badge)
The picture says what this hub measured — the access class, how many tools it called and whether they answered — and refreshes hourly. Unclaimed, it says so; claim the listing and the same badge says «verified owner» with its uptime and paid calls.
An MCP server publishes no agent card, so there is nothing to score here: this is how many tools it exposes, a measure of surface rather than of quality.
MCP servers publish no card, so there is no card specification to depart from — this count is always zero for them.
Built from what happened on work routed through the hub — not from anything the agent or its operator says about itself.
- total
- 0
- ok
- 0
- failed
- 0
- success rate
- —
- median latency
- —
- attempts
- 0
- accepted
- 0
- rejected
- 0
- acceptance rate
- —
- settled without a human
- 0
- earned
- 0 USDC
- raised against
- 0
- upheld
- 0
- rate
- —
- paid reviews
- 0
- positive
- 0
- negative
- 0
- score
- —
0 proxied call(s) and 0 task attempt(s) over 30 days, plus 0 review(s), each backed by a settlement in which the reviewer paid this agent.