simplefunctions
io.github.spfunctions/simplefunctions
Calibrated world model for AI agents. 40 tools: world state, markets, trading. Kalshi + Polymarket.
— the operator's own registry description reported
Publisher io.github.spfunctions · first seen 2026-08-12 · endpoint https://simplefunctions.dev/api/mcp/mcp
Dependency rating derived
Cluster rich-solo · distinctiveness 0.354 (moderate). Every figure is a percentile or class within the 11,094-server census — see the whole spectrum.
🔏 Signed receipt rr_4320b39e88165af231a2a271 · ed25519 · key rs-rcpt-2026-08 — this rating is tamper-evident; an agent gets the full signature from check_server and can verify it against the published key.
What kind of tools these are derived
Verification only means something relative to a tool's NATURE — an email-sender has no "true answer", a generator has no answer key. This server's 108 tools, classified, with what checking applies to each kind (the full methodology →):
| nature | tools | meaning | what checking applies |
|---|---|---|---|
| retrieval-public | 47 | serves public facts | truth-checkable against a public source — the V-ladder applies in full |
| action | 32 | changes the world | no true answer exists; we check the CONTRACT (destructive/read-only/idempotent declarations, error legibility) and never fire real actions |
| predictive | 14 | claims about the future | scoreable only in retrospect — the archive scores yesterday's predictions against today's outcome |
| unclassified | 9 | not yet classifiable from its text | Tier-1 only until its tools describe themselves |
| retrieval-private | 3 | serves the caller's own data | outside truth-checking is impossible BY NATURE, not by failure — the operator-invited pathway applies |
| computational | 2 | deterministic transforms | self-checkable by re-computation and known-answer tests |
| generative | 1 | creates content | no answer key exists; disclosure + stability checks, never truth verdicts |
Tools last seen
Harness readiness observed
Can an agent's harness pick this tool and call it correctly? Graded on the three things an agent reads — name, description, typed parameters. Band A — an agent can pick and call these reliably.
| legibility check | tools passing | ok |
|---|---|---|
| name is clear & specific | 107/108 | 107/108 |
| has a description | 108/108 | ✓ |
| description is substantive | 102/108 | 102/108 |
| parameters are typed | 108/108 | ✓ |
| parameters are described | 98/108 | 98/108 |
108 of 108 tools graded · 108 with a captured input schema. RS-008, Tier-1 — no domain knowledge, applies to any tool. “Alive” is not the same as “usable”.
Truth checks observed
0/0 answers agree with the published primary source · 2 unverifiable.
| claim class | key | verdict | primary source |
|---|---|---|---|
| tariff-duty | 6109.10.00 | unverifiable | us-hts |
| tariff-duty | 8471.30.01 | unverifiable | us-hts |
Protocol conformance observed
Capabilities: tools
Drift
No confirmed drift on record. Baseline set 2026-08-14; changes appear here after human review.
History observed
Every probe we made, oldest → newest (2 shown, 2026-08-12 → 2026-08-14). Green answered · amber answered-but-walled · red no useful answer. A gap in our cadence is a gap in coverage, not evidence about the server.
changelog (1 events)
| date | type | what changed |
|---|---|---|
| 2026-08-12 | outcome | first probe: ok_tools |
raw probe records
| probed (UTC) | outcome | http | ms | protocol |
|---|---|---|---|---|
| 2026-08-14T20:00:13Z | ok_tools | 200 | 166 | 2025-06-18 |
| 2026-08-12T05:35:25Z | ok_tools | 200 | 156 | 2025-06-18 |
Watch or embed this verdict
Operators: put the live verdict in your README — it updates with every census, links back here, and is a dated observation, never a warranty:
[](https://robinsaige.com/s/io.github.spfunctions/simplefunctions)
Depend on it? Subscribe to its change feed — outcome changes and confirmed drift, no account needed. Building on it? The full dossier as JSON — verdict, rating, truth checks, history — stable enough to gate CI on.