---
type: "article"
title: "The Demand Report #05 — one in sixteen searches is now an agent"
newsletter: "APIs.io"
newsletter_handle: "apisio"
newsletter_url: "https://usecommune.com/n/apisio"
author: "Kin Lane (@kinlane)"
published: "2026-08-17T18:45:11.051Z"
canonical_url: "https://usecommune.com/n/apisio/a/MNyXfVwR"
markdown_url: "https://usecommune.com/n/apisio/a/MNyXfVwR.md"
chat_url: "https://usecommune.com/n/apisio/a/MNyXfVwR/chat"
body_source: "native"
likes: 0
replies: 0
body_words: 2021
---

# The Demand Report #05 — one in sixteen searches is now an agent

*Agent searches set another record while everything else halved, the whole catalog was rescored on a new rubric, and an African carrier is the only agent-native provider on this week's board.*

**Week of August 10 – 16, 2026 · 26,575 providers · 115,308 APIs indexed**

***

Every Monday I read what people and agents actually typed into [apis.io](https://apis.io/) — the search box and the MCP server — as a demand signal for the API economy. Nobody else has this data, so nobody else can send you this email.

***

## 📈 The Demand Report

**One in sixteen searches now arrives through the MCP server.** Agent searches hit **2,768** — an all-time high, the second record week running — and they did it in a week when total search volume fell by more than half.

The MCP series now reads 35 → 42 → 310 → 1,027 → 518 → **1,924 → 2,768**. As a share of everything: 0.1% → 0.3% → 0.8% → 2.7% → 0.4% → 2.0% → **6.3%**.

![This week vs last: total searches −53% to 44.2k, keyless API −80% to 12.7k, unique terms −3.8% to 5,338, MCP searches +44% to 2,768. Footnote: the volume that left was automated; unique terms held near-flat and MCP hit a new high](https://file+.vscode-resource.vscode-cdn.net/Users/kinlane/GitHub/api-search/newsletter/issue-05-scoreboard.png)

**The three red numbers are one story and the green one is another.** Requests are logged by tier: `internal` is the apis.io site calling itself and every crawler walking those pages; `keyless` is somebody hitting the API directly from outside.

|   | Last week | This week |   |
| --- | --- | --- | --- |
| Internal (the site itself) | 31,048 | **31,494** | \+1.4% |
| Keyless API (outside callers) | 63,838 | **12,718** | −80% |
| MCP server | 1,924 | **2,768** | **+44%** |
| Unique terms | 5,547 | **5,338** | −3.8% |

Last issue the keyless tier jumped 1,112% and I said flat distinct terms meant that was one automated caller changing doors rather than new buyers. It left. Keyless fell 80%, the site's own tier didn't move at all, and **distinct search terms went 5,595 → 5,547 → 5,338 across three weeks** — a 4.6% drift while headline volume went 123k → 95k → 44k.

That is the number to plan against. Roughly **5,300 to 5,600 distinct things asked for per week** is the durable demand line here, and it has now survived a crawler arriving and a crawler leaving without moving much.

**Concentration check:** the top 100 terms account for just 2,004 of 44,212 requests, and 1,267 of those 2,004 are two machine callers — *"Automation Preflight API"* at 1,091 (down from 1,988) and *"AVORA Agent Forge"* at 176. Strip those two and the top 100 is 737 requests spread across a very long tail. Demand here is wide and shallow, not concentrated.

**Underneath, the human vocabulary is unglamorous and specific:** `edi` (15), `RAG` (13), `selling partner` (10), `web search` (10), `LexisNexis` (11), `42crunch` (8), `json-rpc` (8), `time-series` (8), `Autonomous Vehicles` (8). Integration plumbing and named vendors, not categories.

**On the Pro tier:** 23 attempts on `ratings`, 4 on `compare`, 3 on `gaps`, 2 each on `areas` and `changes`. `ratings` has been the most-reached-for gated resource every single week I've run this report.

***

## 🕳️ The Gaps (demand we couldn't answer)

The pipeline saw **393 raw unmet terms**, dropped 27 as noise, and kept **366**. I then re-probed all 100 published zero-result terms against the live API this morning: **19 of them now return results and 81 genuinely do not.** These eight are from the 81.

![The Gaps — top zero-result searches: Radar Connection Tampering 4×, Reutersconnect and Predictiveindex 3×, then Bedrock Converse API, Bedrock Runtime API, ANVR G7, A10networks and Envia.mx at 2× each](https://file+.vscode-resource.vscode-cdn.net/Users/kinlane/GitHub/api-search/newsletter/issue-05-gaps.png)

- **AWS Bedrock** (6× across three spellings) — somebody wanted the Bedrock *Converse* and *Runtime* API schemas and tried `Bedrock Converse API Schema`, `Bedrock Runtime API Schema` and the typo `Bedrock ConverAPI Schema`. Three attempts at the same thing is not idle browsing. This is the sharpest gap of the week: the model-invocation layer everybody is building on, and no contract indexed for it.
- **Radar Connection Tampering** (4×) — a named Cloudflare Radar dataset. Not the company, not the product, the *endpoint*. Someone knew exactly what they wanted.
- **Reutersconnect** (3×) — Reuters' media licensing platform. Content licensing is the API layer every AI company is currently negotiating in private.
- **Predictiveindex** (3×) — talent assessment, in a week where Human Resources & Payroll indexes 867 providers and 4,164 APIs on the network and still misses this one.
- **ANVR G7** (2×) — **second week running.** The Dutch travel trade association's booking-message standard. Somebody wants a *specification* indexed, not a company, and they came back.
- **A10networks** (2×) — application delivery and security.
- **Envia.mx** (2×) — Mexican multi-carrier shipping, alongside four spellings of `nbnco` from someone hunting Australia's national broadband wholesaler by domain.

A model-invocation layer, a network-measurement dataset, a media-licensing platform, a Dutch travel standard, and Mexican logistics. Nothing about that list is a category — every one of them is a specific thing a specific person needed and did not get.

**If you build in one of these lanes, this is your invitation.** Add your API in about two minutes: [**apis.io/add**](https://apis.io/add) — or point your agent at the [apis.io MCP server](https://apis.io/) and let it submit for you.

***

## 🆕 New to the Index

The catalog stands at **26,575 providers and 115,308 APIs**. APIs are up 242 on the week; providers are **down 126** — the first Monday-over-Monday decline in the provider count across the four weeks this report has tracked it, with duplicate merges and retirements running ahead of arrivals. A catalog that only ever grows is a catalog nobody is maintaining.

The submission backlog finished processing this week, and the two batch write-ups are the ones I'd read:

- [**Six of Eight New APIs Ship an MCP Server**](https://apis.io/blog/) — the final batch of eight, and six of them ship a hosted MCP server next to the REST API. Not one is a large company: a positional-astronomy engine, a crypto funding-rate feed, a Georgian legal marketplace, a WebRTC monitor. MCP has stopped being a strategy at these companies and become a checkbox. Across all four batches: **38 providers, 1,286 artifacts, zero failed runs.**
- [**The API Economy Is Not Anglophone**](https://apis.io/blog/) — the third batch, where six of eight declare a home outside the English-speaking tech centres. The one to sit with is **Tvarka**, a single REST API for Lithuanian national eID authentication and qualified electronic signatures — state identity infrastructure as an ordinary HTTP API, from a company almost nobody in this audience has heard of.

Two provider profiles publish over the coming week, and they are a useful pair because they fail in opposite directions:

- [**Siemens**](https://apis.io/providers/siemens/) — 152 APIs listed, **five** machine-readable contracts. Kin Score **40.9 (thin)**, Agent Readiness **30.6 (agent-aware)**. The five specs it does publish are 100% callable and score 68.7 on contract quality; the gap between 152 and 5 is the whole profile *(Industrial)*
- [**MTN Group**](https://apis.io/providers/mtn-group/) — 119 APIs, 115 contracts at **89.6% callable**. Kin Score **47.5 (developing)**, Agent Readiness **51.1 — agent-native**. See below *(Telecommunications)*

**One thing that moved under everyone's feet:** the catalog was rescored today on **Kin Score rubric 0.11.0**. Numbers in this issue are not comparable to numbers in #04. Webex, last issue's subject, reads **51.6** today where it read 58.9 — and its 178 contracts are still 0.0% callable, which was the actual point.

All on the [apis.io blog](https://apis.io/blog).

***

## ⭐ Rated This Week: MTN Group — the only agent-native name on the board

*This week's angle: quietly excellent. Not the top of the index — the provider that beat the giants at the thing that matters.*

[MTN Group](https://apis.io/providers/mtn-group/) scores **47.5, a developing band**, on 119 APIs. Africa's largest mobile operator: ~290 million subscribers across roughly 16 markets, and MoMo, one of the continent's largest mobile-money platforms.

Its composite is middling. Its **Agent Readiness is 51.1, band agent-native** — and that band is the interesting part.

| Facet | Score |
| --- | --- |
| Developer Ergonomics | 62.5 |
| Contract Quality | 60.9 |
| Regulatory (Telecommunications) | 58.3 |
| Discoverability | 57.4 |
| Commercial Clarity | 34.2 |
| Operational Transparency | 21.1 |
| Governance | 20.8 |

**Agent-native is a gated band, not a threshold.** In Agent Readiness 0.2 you need 46 points *and* you must clear a gate: idempotency **and** a stable error envelope. Retries are what separate an agent from a developer — an agent that retries a payment without an idempotency key charges the card twice, and an agent that can't branch on a typed error retries blindly forever.

MTN clears it. Its error semantics are **verified against the contract** — a shared error schema `$ref`'d across responses, not a table of codes in a docs page — and idempotency is documented on the mutating surface.

Here is what that gate does to the scoreboard, all rescored today:

|   | Agent Readiness | Band |
| --- | --- | --- |
| Salesforce | 60.8 | agent-ready — **gated down from agent-native** |
| **MTN Group** | **51.1** | **agent-native** |
| Mastercard | 41.0 | agent-ready |
| Microsoft Graph | 38.7 | agent-ready |
| Siemens | 30.6 | agent-aware |

Salesforce scores nearly ten points higher and is capped, explicitly, for missing idempotency. A Johannesburg carrier ships the safety rail the highest-scoring provider on this board doesn't.

**And the access model is genuinely open.** MADAPI at `developers.mtn.com` lists 221 API products across 15 African markets and lets anyone download the OpenAPI for a product **without an account**. `momodeveloper.mtn.com` is self-serve with a working sandbox for the MoMo Collection, Disbursements and Remittance APIs. Downloading a carrier's contract without registering is rare. Testing a carrier's payment rails in a sandbox without a commercial agreement is rarer. The 89.6% callability comes from TM Forum — 22 TMF Open APIs across the catalog — which is the cheapest route to contract quality a carrier has, and MTN took it.

**The cheapest points on the table:** governance at 20.8 and operational transparency at 21.1 are the two lowest facets on the card and together carry 25% of the composite. There is no published versioning policy, no deprecation practice, and almost no operational signalling — on a surface that moves money in markets where mobile money *is* the banking system. Rate-limit signalling scores a flat zero: MTN publishes no rate-limit artifact and no `RateLimit` headers in its contracts, so an agent driving MoMo has no way to know how close it is to a wall. A status page, a deprecation policy, and rate-limit headers in the response would move both facets and add Agent Readiness points at the same time.

MTN got discovery, access and safety right and hasn't published the governance layer. That is the reverse of the usual enterprise failure, and by far the easier half to fix second.

*Bands, rubric 0.11.0: exemplar 66+ · strong 56–65.9 · developing 42–55.9 · thin 28–41.9 · emerging 13–27.9 · minimal 0–12.9. Agent Readiness 0.2: agent-native 46+ (gated) · agent-ready 34+ · agent-aware 6+ · human-only 0+.*

***

## 🤖 Reproduce this yourself

The band-gate claim is one call and one comparison. Paste into your agent against the [apis.io MCP server](https://apis.io/):

```javascript
get_provider(slug="salesforce", fields=["agent_readiness"])
```

Read `agent_readiness.band_gated_from`. It says `agent-native` — the catalog tells you, in the record, that it capped the band and why. Then run the same call for `mtn-group` and compare `dimensions.idempotency`.

Want the rules rather than my summary of them?

```javascript
get_rating_rubric()
```

That returns every band, every facet weight, and all 111 checks. Grade me with it.

Or read the demand data directly: [**apis.io/search-terms/**](https://apis.io/search-terms/), refreshed every Monday.

***

**26,575 providers. 115,308 APIs. 2,768 agent searches — 6.3% of everything, an all-time high.** See a gap that's yours? → [**apis.io/add**](https://apis.io/add)

*The Demand Report is a weekly read of apis.io's own search + discovery signal. Forward it to someone who ships an API.*

***

## Discussion

No replies yet.