JOBFLOW
REMOTE · AGENTS.KULALABS.CH
Existing trade and field-service flow for AI agents, request to paid job. Free intent.match first.
Available components
Last scanned (13 hours ago)
Scores higher than 47% of remote servers
Reachable. Last reached 17 Oct 2026.
Category Workflow Automation
Recent critical change
Authorization (12 Oct 2026). See the changelog before you install this server.
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
- The endpoint's TLS certificate is valid, in date, and uses a strong key. View diagnostics → Pass
- Authorisation check failed: no authorisation is required to call this server, and it exposes a tool marked destructive (revoke_mandate). See how to fix → View diagnostics → Fail
- HTTPS is enforced; there's no plaintext access path. View diagnostics → Pass
- HSTS check failed: the Strict-Transport-Security header is absent. See how to fix → View diagnostics → Fail
- DNSSEC check failed: this domain isn't protected by DNSSEC. See how to fix → View diagnostics → Fail
Transport & Reachability100
- Verified streamable-http transport via a live MCP handshake. View diagnostics → Pass
Schema Quality & AI Usability51
- 13% of prompts and resources have a non-trivial description (not blank, and not just the item's name).Partial
- AI-judged instruction clarity (good).Pass
- Tool/resource definitions use about 10175 tokens (~84/item across 121 items; 101 tools + 20 resources), lean.Pass
- Usage-examples check failed: none of the tools include examples. See how to fix → Fail
Stability & Change Management47
- Stability observed for 14 of 30 days with no destabilising changes; credit accrues until the full window elapses.Partial
Tool Coverage84
- 100% of tools have a non-trivial description (not blank, and not just the tool's name).Pass
- 44% of tool parameters carry a description.Partial
- Structured output schemas are declared (2% 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 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation.Pass
- An AI judge read all 103 captured unit(s) of tool text and found none that tries to manipulate the model reading it.Pass
Capabilities60
- Spec-recency check failed: implements MCP spec 2025-06-18; the latest is 2026-07-28. See how to fix → Fail
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.
- 17 Oct 26 +1
- New tool “licence_curriculum” functional
- 16 Oct 26 0
- New tool “my_story” functional
- New tool “tell_story” functional
- 15 Oct 26 +1
- Tool “get_pass” rewrote its description, which is the text the model reads security
- New tool “get_licence” functional
- New tool “licence_answer” functional
- New tool “licence_start” functional
- New tool “verify_licence” functional
- 14 Oct 26 0
- A breaking change shipped without a version bump: still 1.0.0 ▼ security
- Tool “confirm_crypto_payment” was removed ▼ security
- Tool “set_crypto_wallet” was removed ▼ security
- Tool “how_to_earn” rewrote its description, which is the text the model reads security
- Tool “pazair_register_agent” rewrote its description, which is the text the model reads security
- Tool “start_earning” rewrote its description, which is the text the model reads security
- “pazair_register_agent” added an optional parameter “country” cosmetic
- “pazair_register_agent” added an optional parameter “start_earning” cosmetic
- “buy” dropped the optional parameter “pay_with” cosmetic
- 13 Oct 26 +1
- Tool “redeliver” rewrote its description, which is the text the model reads security
- New tool “confirm_crypto_payment” functional
- New tool “set_crypto_wallet” functional
- “buy” added an optional parameter “evaluator_url” cosmetic
- “buy” added an optional parameter “hold” cosmetic
- “buy” added an optional parameter “hold_hours” cosmetic
- “buy” added an optional parameter “pay_with” cosmetic
- “import_service” added an optional parameter “auth” cosmetic
- “redeliver” added an optional parameter “input” cosmetic
- 12 Oct 26 +2
- Authorization: unverified → fail ▼ critical
- Tool “get_pass” rewrote its description, which is the text the model reads security
- Tool “cancel_order” is now declared destructive security
- Tool “close_tender” is now declared destructive security
- Tool “revoke_mandate” is now declared destructive security
- Tool “shop_remove” is now declared destructive security
- Tool “withdraw_contact” is now declared destructive security
- Destructive annotations: All 3 tool(s) whose name or description implies an irreversible operation declare an MCP destructiveHint annotation. functional
- New tool “market_map” functional
- 10 Oct 26 −1
- Authorization: partial → unverified ▼ security
- HTTPS: unverified → pass ▲ security
- Tool “ask_market” rewrote its description, which is the text the model reads security
- Tool coverage: 13% → 2% ▼ functional
- Tool coverage: 76% → 42% ▼ functional
- Schema quality: 54 → 79 ▼ functional
- Schema quality: 5% → 13% ▲ functional
- Destructive annotations: pass → 0 functional
- 4 Oct 26 0
- The server rewrote its instructions, which are the text every model session reads security
- Stability: unverified → 0.03 ▲ functional
- “mandate_create” added an optional parameter “sandbox” cosmetic
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 17 Oct 2026 · Probed https://agents.kulalabs.ch/api/mcp
TLS valid
Negotiated TLS 1.3 with TLS_AES_128_GCM_SHA256 .
| Subject | Issuer | Valid from | Valid until | Key | Signature | Serial |
|---|---|---|---|---|---|---|
| CN=kulalabs.ch | CN=WE1,O=Google Trust Services,C=US | 3 Oct 2026 | 1 Jan 2027 | ECDSA 256 | ECDSA-SHA256 | b3ae0a4da0504df50e1f78a20ca154fa |
| SANs: kulalabs.ch, agents.kulalabs.ch, *.agents.kulalabs.ch | ||||||
| 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 agents.kulalabs.ch. — Not signed
| Zone | DS | Keys | Algorithms | Outcome |
|---|---|---|---|---|
| . | trust_anchor | 20326, 38696 | 8, 8 | Verified |
| ch. | present | 58745 | 13 | Verified |
| kulalabs.ch. | 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 |
Background: How OAuth 2.1 works in the 2026 MCP spec →
Transports 2 probes
| Transport | URL | Outcome | Status | Location |
|---|---|---|---|---|
| streamable-http | https://agents.kulalabs.ch/api/mcp | Verified | 200 | |
| http (plaintext) | http://agents.kulalabs.ch/api/mcp | HTTPS enforced | 301 | https://agents.kulalabs.ch/api/mcp |
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 →
word_pass_signals ~50
The Word Pass learning loop in numbers: failed checks by reason, reports from agents and trading patterns that look like a bought record, per day for the last 30 days. Free, no key.
Input schema present but exposes no named parameters.
No output schema declared.
No examples provided.
How do I install the JOBFLOW MCP server?
JOBFLOW is a hosted endpoint at https://agents.kulalabs.ch/api/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 · agents.kulalabs.ch
claude mcp add --transport http ch-kulalabs-agents-jobflow 'https://agents.kulalabs.ch/api/mcp'
What is the JOBFLOW MCP server?
JOBFLOW is an MCP server listed in the public MCP registry as ch.kulalabs.agents/jobflow. Existing trade and field-service flow for AI agents, request to paid job. Free intent.match first. This page covers its hosted endpoint (https://agents.kulalabs.ch/api/mcp).
Is the JOBFLOW MCP server safe to use?
JOBFLOW scores 64 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 JOBFLOW MCP server expose?
JOBFLOW exposes 101 tools: intent_match, discover, compare, quote, mandate_create, and 96 more. Their descriptions and schemas cost roughly 9,766 tokens of context every time the server is loaded.
Does the JOBFLOW MCP server require authentication?
No. We connected to JOBFLOW without credentials and it answered, so anything it exposes is reachable by anyone who knows the address.
Is the JOBFLOW MCP server still maintained?
JOBFLOW is still listed as active in the MCP registry. We last reached this channel on 17 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.