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.

humans fix ai

REMOTE · HUMANSFIX.AI

Ask a real, manually approved developer for help. Nothing is sent until you say yes.

Available components

0 this week 79 Trust /100

Last scanned (15 hours ago)

Scores higher than 74% of remote servers

Reachable. Last reached 21 Nov 2026.

Category Developer Tools

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 Security97
Transport & Reachability100
Schema Quality & AI Usability69
  • AI-judged instruction clarity (excellent).Pass
  • Context-footprint check failed: tool/resource definitions use about 725 tokens (~181/item across 4 items; 4 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 Management0
  • Stability check failed: schema churn in the 13 days we've observed: 0 tool removals, 1 breaking changes, 0 auth/transport breaks, 3 additions. See how to fix → Fail
Tool Coverage100
  • 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
  • 100% of tool parameters carry a description.Pass
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 5 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.

  • 14 Nov 26 0
    • Tool “ask_human_developer” rewrote its description, which is the text the model reads security
    • Tool “get_task_status” rewrote its description, which is the text the model reads security
    • Tool “respond_to_call_time” rewrote its description, which is the text the model reads security
    • Tool “send_request” rewrote its description, which is the text the model reads security
    • Tool “respond_to_call_time” is now declared destructive security
    • Schema quality: 226 → 181 ▲ functional
    • “send_request” reworded the description of “text” cosmetic
  • 13 Nov 26 0
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ask_human_developer” rewrote its description, which is the text the model reads security
    • Tool “get_task_status” rewrote its description, which is the text the model reads security
    • Schema quality: 664 → 907 ▼ functional
    • Destructive annotations: pass → 100 functional
    • New tool “send_request” functional
  • 12 Nov 26 +5
    • Stability: 0.10 → fail ▼ security
    • Authorization: partial → pass ▲ security
    • First check of Authorization: pass security
    • The server rewrote its instructions, which are the text every model session reads security
    • Tool “ask_human_developer” rewrote its description, which is the text the model reads security
    • “ask_human_developer” dropped the required parameter “email” ▼ functional
    • Schema quality: 320 → 221 ▲ functional
    • Server version: 1.0.1 → 2.0.0 functional
    • New tool “get_task_status” functional
    • New tool “respond_to_call_time” functional
  • 11 Nov 26 +1

    No change was recorded against any check on this day. Stability & Change Management went from 7 to 10. That category is still filling its 30-day observation window: 2 days of observed history at the previous scan, 3 at this one. The score rises as the window fills, whether or not the server changes.

  • 9 Nov 26 +1
    • Stability: unverified → 0.03 ▲ functional
    • Server version: 1.0.0 → 1.0.1 functional
  • 8 Nov 26 72

    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://humansfix.ai/mcp

TLS valid

Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .

Subject Issuer Valid from Valid until Key Signature Serial
CN=humansfix.ai CN=YE1,O=Let's Encrypt,C=US 16 Oct 2026 14 Jan 2027 ECDSA 256 ECDSA-SHA384 59b32e584ab82787411fbb11f5d82b0fc90
SANs: humansfix.ai, www.humansfix.ai
CN=YE1,O=Let's Encrypt,C=US (CA) CN=Root YE,O=ISRG,C=US 3 Sept 2025 2 Sept 2028 ECDSA 384 ECDSA-SHA384 5ddd70dd31f801c85c186a7a04b80afe
CN=Root YE,O=ISRG,C=US (CA) CN=ISRG Root X2,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 ECDSA-SHA384 872165fc34b6e5fba8add5b3705fb53a
CN=ISRG Root X2,O=Internet Security Research Group,C=US (CA) CN=ISRG Root X1,O=Internet Security Research Group,C=US 13 May 2026 2 Sept 2032 ECDSA 384 SHA256-RSA 6c8f1dc727c7117f7baf853ac980f9cd

Background: What to check on a remote MCP endpoint →

DNSSEC insecure

Validation of humansfix.ai. — Not signed

Zone DS Keys Algorithms Outcome
. Trust anchor 20326, 38696 8, 8 Verified
ai. DS published 1814 8 Verified
humansfix.ai. No DS 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://humansfix.ai/.well-known/oauth-protected-resource/mcp", scope="tasks.read tasks.write"

Bearer resource_metadata="https://humansfix.ai/.well-known/oauth-protected-resource/mcp", scope="tasks.read tasks.write"
Header Value
strict-transport-security max-age=31536000 ; includeSubDomains
content-security-policy default-src 'self'; script-src 'self' 'unsafe-inline' https://www.googletagmanager.com; style-src 'self' 'unsafe-inline' https://fonts.googleapis.com; font-src 'self' https://fonts.gstatic.com; img-src 'self' data: https: http:; connect-src 'self' https://www.google-analytics.com https://analytics.google.com https://*.google-analytics.com; frame-src 'self'; form-action 'self' https://*.stripe.com; base-uri 'self'; object-src 'none'
x-content-type-options nosniff
x-frame-options SAMEORIGIN
referrer-policy strict-origin-when-cross-origin
permissions-policy camera=(), microphone=(), geolocation=()

Protected resource metadata

Document https://humansfix.ai/.well-known/oauth-protected-resource/mcp
Retrieved Yes
Resource https://humansfix.ai/mcp
Authorisation server https://humansfix.ai

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

Transports 2 probes
Transport URL Outcome Status Location
streamable-http https://humansfix.ai/mcp Verified 200
http (plaintext) http://humansfix.ai/mcp HTTPS enforced 301 https://humansfix.ai/mcp
MCP tools · 4 exposed · ~608 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
ask_human_developer ~182

Saves a draft request to a real, manually approved human developer: a question, a code review, a consultation or hands-on help with a software problem. It takes a short summary in plain words, which must not contain passwords, API keys, tokens or other secrets. Only a draft is saved: nothing reaches a developer until it is sent, and nothing is charged. It returns the exact saved text and a task_id.

NameTypeReqDescription
availabilitystring–When the person is free for a call, for example 'weekdays after 5pm CET'. Optional.
summarystringyesWhat the person needs, in plain words: what is wrong or what they want help with, what they were doing, and what has already been tried. No secrets.
toolstring–The AI tool the app was built with, if known.

No output schema declared.

No examples provided.

get_task_status ~121

Returns where the user's requests stand: a fixed state, a next_action (send_request, respond_to_call_time, person_decides_on_website, join_call, wait or none), the call time in the user's own time zone and a link to the request page. With no task_id it lists the most recent requests. Read-only. It never returns text written by a developer. Prices, approvals and cards are never handled by this connector.

NameTypeReqDescription
task_idstring–The request to look at. Leave it out to list the most recent ones.

No output schema declared.

No examples provided.

respond_to_call_time ~175

Answers a call time for a request. 'accept' confirms the time a developer proposed, or the new time a developer asked for. 'decline' says it does not work: before the call is booked another developer is asked, afterwards the booked time stays. 'propose_other_time' suggests a new time for a booked call; the developer is emailed and answers. Times are shown in the user's own time zone; new times are ISO 8601 with an offset.

NameTypeReqDescription
actionstringyesWhat the person chose.
task_idstringyesThe request the call is for.
timestring–Only for propose_other_time: the new start as ISO 8601 with an offset, for example 2026-11-12T15:00:00+01:00.

No output schema declared.

No examples provided.

send_request ~130

Sends a saved draft to approved developers. It works only for a draft this connection saved in the last 30 minutes, and each person can send only a few per day. The person receives an email copy with a link to cancel. Nothing is charged. The optional text is compared with the saved draft, and nothing is sent if it differs.

NameTypeReqDescription
task_idstringyesThe draft to send: the task_id that ask_human_developer returned.
textstring–The exact saved text, to confirm what is being sent. If it differs from the saved draft, nothing is sent.

No output schema declared.

No examples provided.

Install

How do I install the humans fix ai MCP server?

humans fix ai is a hosted endpoint at https://humansfix.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 · humansfix.ai

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

What is the humans fix ai MCP server?

humans fix ai is an MCP server listed in the public MCP registry as ai.humansfix/humansfix. Ask a real, manually approved developer for help. Nothing is sent until you say yes. This page covers its hosted endpoint (https://humansfix.ai/mcp).

Is the humans fix ai MCP server safe to use?

humans fix ai scores 79 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 humans fix ai MCP server expose?

humans fix ai exposes 4 tools: ask_human_developer, send_request, get_task_status, respond_to_call_time. Their descriptions and schemas cost roughly 608 tokens of context every time the server is loaded.

Does the humans fix ai MCP server require authentication?

Yes. humans fix ai 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 humans fix ai MCP server still maintained?

humans fix ai 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 humans fix ai MCP server?

VerifyMCP ran 13 checks on humans fix ai, 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.