GAIP Agent Observatory
State of public AI agents, October 2026
What GAIP observed across public MCP servers and A2A agents: how many answered, which protocol versions they report, how many ask for credentials and which discovery standards hosts publish. Aggregate facts only; no party is scored or ranked.
GAIP Agent Web Index — October 2026 (provisional: the month has not ended)
Declared versus observed: what public AI agents declared and what changed this month. Headline figures count every public agent or host GAIP read this month (12525 agents watched). Beside each: the frozen panel AGENTS-COHORT-2026-10, 4157 public MCP servers and A2A agents on 3676 hosts. Registry size: no complete walk of the Official MCP Registry was recorded this month (the walk under way has read 49500 entries so far); GAIP watched 12032 of its servers and read 11623 of them in the last 7 days. Aggregates only: a count is shown only when it and its total are at least 5; no host, agent or caller is named; facts are as observed by GAIP at the stated time and assess no one. A month is final only after it ends; until then it is provisional.
| Figure | All watched agents | Out of | Panel AGENTS-COHORT-2026-10 | Out of |
|---|---|---|---|---|
| Agents whose declared tools changed | under 5 (not shown) | every public MCP server and A2A agent GAIP watched when this copy was built (all sources; hosts an outside caller asked about and GAIP's own agents left out); the agents counted are among them | under 5 (not shown) | every member of the frozen panel AGENTS-COHORT-2026-10 |
| Hosts whose declared terms, limits or prices changed | too few to show (under 5) | every public host whose declared terms GAIP read this month (hosts an outside caller asked about and rows under a method version with a known defect left out) | too few to show (under 5) | panel hosts whose declared terms GAIP read this month (agent_terms rows) |
| Agent cards carrying a signature | too few to show (under 5) | every public host whose A2A agent card GAIP read this month (latest read; hosts an outside caller asked about and rows under a method version with a known defect left out) | too few to show (under 5) | panel hosts whose A2A agent card GAIP read this month (latest read) |
| Most frequent failure types diagnosed for outside callers | too few diagnoses to show (under 5 per type) | front-door gaip_diagnose answers to outside callers this month | ||
| Hosts carrying any AI-preference signal | too few to show (under 5) | every agent host whose robots.txt or responses GAIP read this month (latest read; hosts an outside caller asked about and rows under a method version with a known defect left out) | too few to show (under 5) | panel hosts whose robots.txt or responses GAIP read this month (latest read) |
| Agent prices (x402 Bazaar listings) | not collected yet (switched off until the founder confirms the source terms) | |||
| ERC-8004 agent registration files | not collected yet (switched off until the founder confirms the source terms) | |||
| Reachability and response times (the 30 days to 3 October 2026) | 99.2% of 17252 visits reachable; 99.0% of 9702 agents reachable on at least 95% of visits; response time p50 224 ms, p95 1067 ms | |||
| Reachability and response times, panel AGENTS-COHORT-2026-10 | 99.5% of 11073 visits reachable; 99.4% of 3528 agents reachable on at least 95% of visits; response time p50 222 ms, p95 1087 ms | |||
Cite as: GAIP Agent Web Index, October 2026, gaipagents.com/state-of-agents?month=2026-10, CC BY 4.0. Machine-readable: /v1/free/agent-web-index. How to reproduce each figure: /v1/free/agent-web-index/queries.
Reachability and response times: the 30 days to 3 October 2026 (provisional)
Aggregate facts observed by GAIP at the stated times: how often public agents answered and how fast. Not an assessment of any party; no agent or host is named. Cells under 5 agents are withheld.
| Cohort | Protocol | Figures |
|---|---|---|
| All public agents | MCP and A2A | 99.2% of 17252 visits reachable; 99.0% of 9702 agents reachable on at least 95% of visits; response time p50 224 ms, p95 1067 ms |
| All public agents | MCP | 99.2% of 15723 visits reachable; 99.0% of 9229 agents reachable on at least 95% of visits; response time p50 232 ms, p95 1087 ms |
| All public agents | A2A | 99.5% of 1529 visits reachable; 99.2% of 473 agents reachable on at least 95% of visits; response time p50 158 ms, p95 810 ms |
| Panel AGENTS-COHORT-2026-10 | MCP and A2A | 99.5% of 11073 visits reachable; 99.4% of 3528 agents reachable on at least 95% of visits; response time p50 222 ms, p95 1087 ms |
| Panel AGENTS-COHORT-2026-10 | MCP | 99.5% of 9557 visits reachable; 99.4% of 3068 agents reachable on at least 95% of visits; response time p50 235 ms, p95 1107 ms |
| Panel AGENTS-COHORT-2026-10 | A2A | 99.5% of 1516 visits reachable; 99.1% of 460 agents reachable on at least 95% of visits; response time p50 158 ms, p95 810 ms |
Cite as: GAIP Agent Reliability Index, the 30 days to 3 October 2026, gaipagents.com/state-of-agents, CC BY 4.0. Downloads: CSV · JSON.
This week so far (2026-W40, provisional)
| Public AI agents and MCP servers in the Observatory | 12544 |
|---|---|
| Observed this week | 12125 |
| Answered at least once | 9687 of 12125 (80%) |
| Median response time (ms) | 224 |
| MCP servers that asked for credentials | 2834 of 11623 (24%) |
| MCP servers listing tools without credentials | 6380 of 11623 (55%) |
| New this week | 12544 |
| Published a new manifest version | 9765 |
| Hosts probed for discovery standards | 195 |
| Protocol versions reported | 0.3: 16, 0.3.0: 258, 1.0: 52, 1.0.0: 8, 2024-11-05: 309, 2025-03-26: 283, 2025-06-18: 990, 2025-11-25: 3938, 2026-07-28: 113, other_categories_under_5_each: 8 |
No weekly snapshot of this month is frozen yet; the first covers 2026-W40 (28 Sep - 4 Oct 2026) and is frozen on 5 Oct 2026.
Delivery outcomes, 2026-10
What happened to calls outside callers made to GAIP's own public agents this month, and the verdicts of the Witness delivery checks they asked for. Counts about GAIP's own service only; no caller or third party is named. A share is shown only when both numbers are at least 5.
Outside calls: 790
| Error | 39 of 790 (5%) |
|---|---|
| Blocked | 297 of 790 (38%) |
| Completed | 454 of 790 (57%) |
| Needed more input | 0 of 790 |
| GAIP agent | Outside calls | Completed | Needed more input | Blocked | Error |
|---|---|---|---|---|---|
| witness | 17 | 11 | 0 | 4 | 2 |
| unattributed | 456 | 419 | 0 | 0 | 37 |
| trust-assurance | 11 | 9 | 0 | 2 | 0 |
| listing-observer | 1 | 0 | 0 | 1 | 0 |
| procurement-verify | 285 | 1 | 0 | 284 | 0 |
| integration-protocol | 20 | 14 | 0 | 6 | 0 |
Witness delivery checks: 0
| Met the registered terms | 0 of 0 |
|---|---|
| Did not meet the registered terms | 0 of 0 |
| Could not be decided | 0 of 0 |
Outcome ledger, 2026-10
GAIP's own outcome ledger: one row per month of what happened in agent work GAIP saw, for outside callers only, frozen after the month ends and hash-chained to the month before (never changed or deleted; the chain head is signed in the daily Sigstore anchor). Counts only; categories under 5 are folded together; no caller or third party is named.
This month's row is frozen once the month has ended (from 1 November 2026).
Cite this
GAIP Agent Observatory, State of public AI agents, October 2026. https://www.gaipagents.com/state-of-agents?month=2026-10 Capability change-log head SHA-256 9cc5c7a61a3989d1eeeee04ad4f89ffd6ae4bbfeffbecd95ab5c780672ef620a (9131 entries).
Machine-readable: /v1/free/state-of-agents. Weekly snapshots, hash-chained: /v1/free/ecosystem/snapshots. Method: /methodology. Aggregate figures are licensed under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/): reuse them freely with credit to the GAIP Agent Observatory and the citation shown. Founder decision #13, 1 Oct 2026.