The idea
One command.
Point ToolLens at an MCP server and a set of requests. It tells you which tools the models mix up, how often, and why.
toollens run -s "python server.py" -t tasks.jsonl -m ollama:qwen3:4b
WorkSelected builds
Pet projects I build in my own time, to learn something properly or to fix a problem I keep running into.
My professional work stays confidential, so none of it is here. Everything on this page is personal, built and shipped on my own.
01 · Developer tooling · 2026
Find out which MCP tools your agents confuse, before your users do.
01The problem I hit
My agents kept calling the wrong tool, and nothing told me.
I was wiring MCP servers into agents, mostly on small local models. They'd pick list_events when they needed find_free_slots, or call nothing at all. The only way to find out was trial and error in a chat window.
The idea
Point ToolLens at an MCP server and a set of requests. It tells you which tools the models mix up, how often, and why.
toollens run -s "python server.py" -t tasks.jsonl -m ollama:qwen3:4b
01 · Inspect
Over stdio or Streamable HTTP. It snapshots every tool the server exposes. Here that's a 10-tool calendar server.
02 · Lint
Similar tool pairs, missing "use this when / not for" guidance, undocumented parameters and oversized schemas. Eight rules, TL000 to TL007.
03 · Generate
Direct requests, near-misses that lure toward a sibling tool, and out-of-scope requests where the right answer is to call nothing.
04 · Validate & run
Local runtimes, cloud APIs and an offline BM25 router all face the same validated tasks, so scores stay comparable over time. Nothing gets executed. It scores the decision.
05 · Score
Rows are the tool a request needed, columns the tool the model picked. Amber is confusion. Grey is a missed call.
06 · Rewrite
Only the descriptions changed. Accuracy nearly doubled, and the matrix shows the trade-off: richer text also pulled in more false calls.
07 · Gate
One flag turns a run into a CI check, and a report diff shows what a description change actually did.
toollens run … --fail-under 0.9 --html report.html
02What I built
Now it's a number I can track, and a check that fails the build.
I rewrite a description, rerun the same fixed tasks, and see exactly which mix-ups went away and which new ones appeared.
About these numbers. They come from the offline BM25 router, which rewards shared vocabulary, so they overstate how much wording matters to a capable LLM. The demo shows the workflow. Run your own model to get the number that matters for your stack.
02 · Market data · 2026
Every open Indian IPO, read at a glance, twice a day.
01The problem I hit
One IPO's numbers lived on three pages, and they rarely agreed.
The schedule was in one place, the grey market premium in another, live subscription in a third. Names were spelled differently and dates came without a year. And one source changed its layout four times in a single week.
The idea
Twice a day it collects the facts on every open IPO and gives each one a colour, healthiest first, in a single email.
01 · Gather
Schedule, premium and subscription each come from their own source. A slow source gets retried, and a missing figure reads as unknown, never as zero.
02 · Self-heal
Columns are found by their headers. When the headers change, they're inferred from the numbers themselves and only accepted if the arithmetic holds. The drift still gets reported.
listing = price + premium · % = premium ÷ price
03 · Join
Each IPO is joined across sources and cross-checked three ways. An ambiguous match is refused, so no company inherits another's numbers.
04 · Score
Premium level, premium trend, institutional demand and issue type, scored against thresholds each reader sets for themselves.
05 · Remember
Each run is logged. The trend is this reading minus the last one, and the log is how the scoring will eventually be checked against real listings.
06 · Notify
One email per reader, covering the whole board. If nothing moved since the last run, nobody hears from it.
07 · Serve
Read-only, versioned and keyed. Responses come from the latest run and are never computed on request, so API traffic can't reach the sources.
GET /v1/ipos?status=open
02What I built
Now a layout change is a line in the log, not a wrong number.
Sources still change without warning. IPO Radar reads through the change and flags it, and no reader's inbox ever shows it.
03The facts API
null is not 0."Not published yet" and "published, and zero" are different answers.GET /v1/ipos?status=open
x-api-key: ••••••••••••
200 OK
{
"as_of": "2026-09-01T15:00:12+05:30",
"check_type": "final",
"count": 1,
"ipos": [{
"id": "esds-software-solution",
"type": "mainboard",
"status": "open",
"issue_price": 429.0,
"gmp_percent": 58.28,
"qib": 272.19,
"listing_price": null
}]
}
Not investment advice. IPO Radar reports data against thresholds each reader sets, and never tells anyone what to do. Grey market premiums are unofficial, and the scoring is a heuristic that hasn't been statistically validated yet. That's what the log is for.
NextSay hello