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.

HoldKit

REMOTE · HOLDKIT.PEERFOUNDRY.AI

Idempotency keys, locks, timers, and inboxes for agents over MCP. No payments.

66 Trust /100

Last scanned (2 hours ago)

Scores higher than 52% of remote servers

Reachable. Last reached 5 Nov 2026.

Category Workflow Automation

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 Security63
Transport & Reachability100
Schema Quality & AI Usability72
  • 100% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Pass
  • AI-judged instruction clarity (fair).Partial
  • Tool/resource definitions use about 734 tokens (~48/item across 15 items; 14 tools + 1 resources), lean.Pass
  • Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management17
  • Stability observed for 5 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage67
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 0% of tool parameters carry a description.Fail
Tool Safety100
  • No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.Pass
  • All 1 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
  • An AI judge read all 15 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
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.

  • 5 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 13 to 17. That category is still filling its 30-day observation window: 4 days of observed history at the previous scan, 5 at this one. The score rises as the window fills, whether or not the server changes.

  • 4 Nov 26 +4
    • Tool “idem.begin” rewrote its description, which is the text the model reads security
    • Tool “idem.commit” rewrote its description, which is the text the model reads security
    • Tool “inbox.ack” rewrote its description, which is the text the model reads security
    • Tool “inbox.create” rewrote its description, which is the text the model reads security
    • Tool “inbox.poll” rewrote its description, which is the text the model reads security
    • Tool “inbox.wait” rewrote its description, which is the text the model reads security
    • Tool “keys.create” rewrote its description, which is the text the model reads security
    • Tool “kv.delete” rewrote its description, which is the text the model reads security
    • Tool “kv.get” rewrote its description, which is the text the model reads security
    • Tool “kv.set” rewrote its description, which is the text the model reads security
    • Tool “lock.acquire” rewrote its description, which is the text the model reads security
    • Tool “lock.release” rewrote its description, which is the text the model reads security
    • Tool “timer.cancel” rewrote its description, which is the text the model reads security
    • Tool “timer.set” rewrote its description, which is the text the model reads security
    • Schema quality: 36 → 48 ▼ functional
    • The server now declares the “resources” capability functional
    • First check of Schema quality: 100 functional
    • New resource “recipe” functional
  • 2 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.

  • 1 Nov 26 0
    • Stability: unverified → 0.03 ▲ functional
  • 31 Oct 26 60

    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 5 Nov 2026 · Probed https://holdkit.peerfoundry.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=peerfoundry.ai CN=WE1,O=Google Trust Services,C=US 31 Oct 2026 29 Jan 2027 ECDSA 256 ECDSA-SHA256 75be6c5a6643926613ffd8060e9980ae
SANs: peerfoundry.ai, holdkit.peerfoundry.ai, *.holdkit.peerfoundry.ai
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 holdkit.peerfoundry.ai. — Not signed

Zone DS Keys Algorithms Outcome
. trust_anchor 20326, 38696 8, 8 Verified
ai. present 1814, 3799 8, 8 Verified
peerfoundry.ai. absent 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
Header Value
strict-transport-security max-age=86400; includeSubDomains
x-content-type-options nosniff

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://holdkit.peerfoundry.ai/mcp Verified 200
http (plaintext) http://holdkit.peerfoundry.ai/mcp HTTPS enforced 301 https://holdkit.peerfoundry.ai/mcp
MCP tools · 14 exposed · ~712 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
idem.begin ~69

Start an idempotency key or return the prior outcome. fingerprint is a hex hash. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
fingerprintstringyes–
keystringyes–
scopestringyes–
ttl_sinteger––

No output schema declared.

No examples provided.

idem.commit ~85

Store the outcome reference for an idempotency key. scope (max 64) and owner are optional. When owner is omitted, the caller key hash is sent. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
keystringyes–
ownerstring––
result_refstringyes–
scopestring––

No output schema declared.

No examples provided.

inbox.ack ~44

Mark inbox events done. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
event_idsarrayyes–
inbox_idstringyes–

No output schema declared.

No examples provided.

inbox.create ~34

Create an inbox. Returns webhook and A2A URLs. Call keys.create once. Pass the key on every tools/call.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

inbox.poll ~51

Read inbox events after a cursor. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
cursorinteger––
inbox_idstringyes–
limitinteger––

No output schema declared.

No examples provided.

inbox.wait ~69

Poll an inbox. block_ms is accepted and capped at 0 in this MVP, so the call returns current events. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
block_msinteger––
cursorinteger––
inbox_idstringyes–

No output schema declared.

No examples provided.

keys.create ~38

Mint a pf_ caller key bound to one HoldKit namespace. The raw key is shown once. Pass this key on every later tools/call.

Input schema present but exposes no named parameters.

No output schema declared.

No examples provided.

kv.delete ~33

Delete a value. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
keystringyes–

No output schema declared.

No examples provided.

kv.get ~34

Read a small value. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
keystringyes–

No output schema declared.

No examples provided.

kv.set ~59

Write a small value with a TTL. Emails and card numbers are rejected. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
keystringyes–
ttl_sintegeryes–
valuestringyes–

No output schema declared.

No examples provided.

lock.acquire ~54

Take a lease lock. Returns a fencing token. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
namestringyes–
ownerstring––
ttl_sintegeryes–

No output schema declared.

No examples provided.

lock.release ~44

Release a lock with its fencing token. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
fencingintegeryes–
namestringyes–

No output schema declared.

No examples provided.

timer.cancel ~34

Cancel a timer. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
timer_idstringyes–

No output schema declared.

No examples provided.

timer.set ~64

Schedule a durable timer. Delivery URLs must be public https. Call keys.create once. Pass the key on every tools/call.

NameTypeReqDescription
delay_sintegeryes–
inbox_idstring––
payloadstringyes–
urlstring––

No output schema declared.

No examples provided.

Install

How do I install the HoldKit MCP server?

HoldKit is a hosted endpoint at https://holdkit.peerfoundry.ai/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 · holdkit.peerfoundry.ai

# add to Claude Code
claude mcp add --transport http ai-peerfoundry-holdkit 'https://holdkit.peerfoundry.ai/mcp'
Common questions

What is the HoldKit MCP server?

HoldKit is an MCP server listed in the public MCP registry as ai.peerfoundry/holdkit. Idempotency keys, locks, timers, and inboxes for agents over MCP. No payments. This page covers its hosted endpoint (https://holdkit.peerfoundry.ai/mcp).

Is the HoldKit MCP server safe to use?

HoldKit 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 HoldKit MCP server expose?

HoldKit exposes 14 tools: keys.create, inbox.create, inbox.poll, inbox.ack, inbox.wait, and 9 more. Their descriptions and schemas cost roughly 712 tokens of context every time the server is loaded.

Does the HoldKit MCP server require authentication?

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

Is the HoldKit MCP server still maintained?

HoldKit is still listed as active in the MCP registry. We last reached this channel on 5 November 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.