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.

Privi Call

REMOTE · PRIVI-CALL-E3RB.ONRENDER.COM

One number per AI agent: route MCP calls to any agent, every call sealed in an on-chain log.

66 Trust /100

Last scanned (15 hours ago)

Scores higher than 51% of remote servers

Reachable. Last reached 21 Nov 2026.

Category AI and Machine Learning

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 Security57
Transport & Reachability100
Schema Quality & AI Usability70
  • AI-judged instruction clarity (good).Pass
  • Context-footprint check failed: tool/resource definitions use about 2101 tokens (~105/item across 20 items; 20 tools + 0 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 Management20
  • Stability observed for 6 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage94
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 79% of tool parameters carry a description.Partial
  • Structured output schemas are declared (35% of tools); any adoption earns full credit.Pass
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 2 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 21 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities100
  • Implements a current MCP spec version (2026-07-28).Pass
What we tested

Checks we ran (13)

  • TLS certificate
  • Authorization
  • HTTPS
  • HSTS header
  • DNSSEC
  • Transport
  • Schema quality
  • Stability
  • Tool coverage
  • Injection markers
  • Destructive annotations
  • Judged manipulation
  • MCP protocol

Does not apply to this hosted endpoint (2)

  • Supply Chain SecurityScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.
  • Provenance & TransparencyScored on package channels only. This is a hosted endpoint, so there is nothing to install or inspect.

The score does not measure everything. What the score does not measure →

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.

  • 21 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 17 to 20. That category is still filling its 30-day observation window: 5 days of observed history at the previous scan, 6 at this one. The score rises as the window fills, whether or not the server changes.

  • 19 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 10 to 13. That category is still filling its 30-day observation window: 3 days of observed history at the previous scan, 4 at this one. The score rises as the window fills, whether or not the server changes.

  • 17 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 3 to 7. That category is still filling its 30-day observation window: 1 days of observed history at the previous scan, 2 at this one. The score rises as the window fills, whether or not the server changes.

  • 16 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 15 Nov 26 63

    First indexed and scored.

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 21 Nov 2026 · Probed https://privi-call-e3rb.onrender.com/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=onrender.com CN=WE1,O=Google Trust Services,C=US 19 Nov 2026 17 Feb 2027 ECDSA 256 ECDSA-SHA256 8d72a13c2c41648513b9d014eb5e0339
SANs: onrender.com, *.onrender.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 privi-call-e3rb.onrender.com. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
com. DS published 19718 13 Verified
onrender.com. No DS Unsigned (proven) parent-signed NSEC/NSEC3 proves an unsigned delegation
Authentication No authorisation required

The endpoint answered without asking for a token. Anyone who knows the URL can reach it.

Result No authorisation required
HTTP status 200

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://privi-call-e3rb.onrender.com/mcp Verified 200
http (plaintext) http://privi-call-e3rb.onrender.com/mcp HTTPS enforced 301 https://privi-call-e3rb.onrender.com/mcp
MCP tools · 20 exposed · ~1,778 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
call_agent ~163

Call a tool on any agent on the Privi Call network and get its answer, with a sealed call record. No Call routing fee for Privi agents (the target tool charges its own x402 price); calls to other agents cost $0.001 each from a call key.

NameTypeReqDescription
arguments––Arguments for that tool
call_keystring–Prepaid call key (pck_...); each call to a non-Privi agent uses one call credit ($0.001)
numberstringyesNumber of the agent to call (call_directory)
payment––x402 payment for a paid target tool; forwarded as _meta['x402/payment']
toolstringyesTool name on that agent (call_list_tools)

No output schema declared.

No examples provided.

call_consent_check ~75

What a person has agreed to, with when and how. With no phone, checks that your consent log is intact.

NameTypeReqDescription
call_keystringyesYour prepaid call key (pck_...); your lists belong to it
phonestring–Phone number; empty to verify your whole consent log instead

No output schema declared.

No examples provided.

call_consent_record ~153

Record that a person agreed to marketing calls, an AI voice, call recording or texts. Records are hash-chained so they cannot be back-filled unnoticed.

NameTypeReqDescription
call_keystringyesYour prepaid call key (pck_...); your lists belong to it
consent_typestringyesmarketing_calls|ai_voice|call_recording|text_messages
evidence_sha256string–SHA-256 of the form, recording or message that shows it
methodstringyesHow consent was given: web_form|written|verbal_recorded|keypress|text_reply|other
phonestringyesPhone number: 10-digit US or international starting with +

No output schema declared.

No examples provided.

call_consent_revoke ~105

Record that a person withdrew consent. With no type, every consent is revoked and the number goes on your do-not-call list.

NameTypeReqDescription
call_keystringyesYour prepaid call key (pck_...); your lists belong to it
consent_typestring–One type, or empty to revoke everything and add the number to your do-not-call list
phonestringyesPhone number: 10-digit US or international starting with +

No output schema declared.

No examples provided.

call_credits_balance ~39

How many prepaid calls a key has left, and today's free calls.

NameTypeReqDescription
call_keystring–Your call key (pck_...)

No output schema declared.

No examples provided.

call_credits_buy ~80

1,000 routed calls to any agent for $1.00 USDC, paid with x402 on Base ($0.001 a call). Returns a call key (pck_...). Call without payment first to get the exact payment requirements.

NameTypeReqDescription
call_keystring–Existing key to top up; empty creates a new key

No output schema declared.

No examples provided.

call_directory ~57

List agents you can call, with their numbers. Privi's own agents (100-103) are always free to call.

NameTypeReqDescription
querystring–Words to match in an agent's name, description or tags; empty lists all

Structured output declared, but exposes no named fields.

No examples provided.

call_do_not_call ~126

Keep your own do-not-call list: add a person who asked not to be called, remove one, or check a number before dialing. Numbers are stored only as salted hashes.

NameTypeReqDescription
actionstring–check | add | remove
call_keystringyesYour prepaid call key (pck_...); your lists belong to it
phonestringyesPhone number: 10-digit US or international starting with +
reasonstring–Why it was added, e.g. 'asked on call 2026-11-13'

No output schema declared.

No examples provided.

call_hours_check ~113

Is it within calling hours (8 a.m. to 9 p.m.) where the called person is, and if not, when the window opens next.

NameTypeReqDescription
end_hourinteger–Narrow the window for stricter state rules
start_hourinteger–Narrow the window for stricter state rules
timezonestringyesIANA timezone where the called person is, e.g. America/Detroit
when––Moment to check (ISO 8601). Default: now

No output schema declared.

No examples provided.

call_list_tools ~45

The tools an agent on the network offers, with their input schemas. Free.

NameTypeReqDescription
numberstringyesThe agent's number from call_directory, e.g. 100

No output schema declared.

No examples provided.

call_log ~93

Recent calls on the network and the phone line, newest first. Each record is hash-chained to the one before it. Arguments, results and phone transcripts are shown only as SHA-256 hashes.

NameTypeReqDescription
channelstring–agent, phone, or empty for both
limitinteger–How many recent calls (1-200)
numberstring–Only calls to or from this number

Structured output declared, but exposes no named fields.

No examples provided.

call_phone_line ~31

The number humans can call to reach the Privi voice agent (pilots, pricing, or the founder).

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

call_precheck ~172

One answer before dialing: is the number on your do-not-call list, is it within calling hours where the person is, and do you hold the consent this call needs. Returns go / no-go with the reasons.

NameTypeReqDescription
ai_voiceboolean–The call uses an AI or prerecorded voice
call_keystringyesYour prepaid call key (pck_...); your lists belong to it
phonestringyesPhone number: 10-digit US or international starting with +
purposestring–marketing | informational
recordingboolean–The call will be recorded
timezonestringyesIANA timezone where the called person is, e.g. America/Detroit
when––Planned call time (ISO 8601). Default: now

No output schema declared.

No examples provided.

call_register_agent ~119

Give your MCP server a Privi number so any agent can call it through the network. Free. We check that it answers tools/list first. Returns the number and a secret to remove it later.

NameTypeReqDescription
contactstring–Optional email for the owner (never shown publicly)
descriptionstringyesWhat it does, one or two sentences
endpointstringyesPublic https:// MCP endpoint (streamable HTTP)
namestringyesYour agent's name
tags––Up to 8 topic tags

No output schema declared.

No examples provided.

call_unregister_agent ~44

Take your agent off the Privi Call network.

NameTypeReqDescription
numberstringyesYour agent's number
remove_secretstringyesThe secret call_register_agent returned

No output schema declared.

No examples provided.

call_verify_log ~28

Recompute every hash in the call log and show the latest on-chain checkpoint of its head.

Input schema present but exposes no named parameters.

Structured output declared, but exposes no named fields.

No examples provided.

deep_think_plan ~47

Plan requirements, testing, risks and edge cases before agent writes code.

NameTypeReqDescription
acceptance_criteriaarrayyes–
goalstringyes–
languagestringyes–

Structured output declared, but exposes no named fields.

No examples provided.

deep_think_redo ~104

Charge $0.01 only for a genuine, explicitly approved changed code snapshot. A signed x402 wallet payload in MCP _meta['x402/payment'] is still required. No permission to spend customer funds is inferred from the agent's claims.

NameTypeReqDescription
approve_usdc_chargebooleanyes–
new_sha256stringyes–
prior_sha256stringyes–
task_idstringyes–
task_tokenstringyes–

No output schema declared.

No examples provided.

deep_think_review ~58

Log a source hash and five self-reported checks; first submission is free.

NameTypeReqDescription
checksobjectyes–
source_sha256stringyes–
task_idstringyes–
task_tokenstringyes–

Structured output declared, but exposes no named fields.

No examples provided.

privi_token_market ~126

PRIVI on Base: price, how much PRIVI and USDC the Privi swap desk holds (so whether a swap can fill), any Uniswap v3 / Aerodrome pools, and optionally a swap quote. Every paid Privi tool also accepts PRIVI. Free.

NameTypeReqDescription
amountstring–Amount to swap in (USDC for buy, PRIVI for sell), e.g. '25'
sidestring–Optional swap quote: 'buy' (USDC -> PRIVI) or 'sell' (PRIVI -> USDC)

Structured output declared, but exposes no named fields.

No examples provided.

Install

How do I install the Privi Call MCP server?

Privi Call is a hosted endpoint at https://privi-call-e3rb.onrender.com/mcp, 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 · privi-call-e3rb.onrender.com

# add to Claude Code
claude mcp add --transport http canoydario847-cloud-privi-call 'https://privi-call-e3rb.onrender.com/mcp'
Common questions

What is the Privi Call MCP server?

Privi Call is an MCP server listed in the public MCP registry as io.github.canoydario847-cloud/privi-call. One number per AI agent: route MCP calls to any agent, every call sealed in an on-chain log. This page covers its hosted endpoint (https://privi-call-e3rb.onrender.com/mcp).

Is the Privi Call MCP server safe to use?

Privi Call scores 66 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 Privi Call MCP server expose?

Privi Call exposes 20 tools: privi_token_market, call_directory, call_list_tools, call_agent, call_register_agent, and 15 more. Their descriptions and schemas cost roughly 1,778 tokens of context every time the server is loaded.

Does the Privi Call MCP server require authentication?

No. We connected to Privi Call without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.

Is the Privi Call MCP server still maintained?

Privi Call is still listed as active in the MCP registry. We last reached this channel on 21 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

What did VerifyMCP test on the Privi Call MCP server?

VerifyMCP ran 13 checks on Privi Call, covering TLS certificate, Authorization, HTTPS, HSTS header and 9 more. Supply Chain Security and Provenance & Transparency do not apply to a hosted endpoint, so they were not tested. The score does not measure everything, and the scoring documentation lists what it leaves out.