Atlas entry
api.
17 capabilities over MCP. First atlas observation.
17 capabilities, 16 of them tools. 9 only read. 2 change records. 1 sends messages. 4 have no reading.◇
AI reading, beta. side-effects v1 on claude-haiku-5.5, calibrated on MCP (golden-3). Only readings above a measured precision count. Counts are tools, not calls: no tool was called.
AI readings summary · beta
The service lists 16 tools, and 12 have AI readings.
send_outreach is read as sending messages to people.
rewrite_outreach is read as changing records.
create_shortlist is read as creating records.
Written by code from the AI readings on this page: it groups them and says nothing they do not.
What an agent can do here
AI readings, beta · Readings on 12 of 16 MCP tools. 1 reads as sending messages.
Moves money
0
No tool read this way.
Deletes or cancels records
0
No tool read this way.
Sends messages to people
1 tool
send_outreach0.88
Changes permissions
0
No tool read this way.
Runs code
0
No tool read this way.
Should ask a person first
0
No tool read this way.
No counted reading 4 tools No reading was counted, so any effect above is possible for them: continue_campaign, find_leads, preview_shortlist, revoke_shortlist.
What changed
First atlas observation. Atlas history
Look first
AI reading, beta: AI adds items here; it never removes one.
send_outreachSends messages to people · 0.88
Surfaces
5 protocols checked
| ARD | Not found | No document retrieved |
|---|---|---|
| A2A | Not found | 0 skills |
| MCP | Valid | 2026-07-28 · 16 tools · 1 resource · prompts not advertised |
| OpenAPI | Not detected | 0 operations |
| WebMCP | Not detected | 0 declarative form tools · experimental |
Exact states and meaning
- ARDabsent
Exact state: not found · No document retrieved
The supported discovery location returned no matching document.
Not found does not prove the service exposes no such interface elsewhere.
Not observed / not fetched
- A2Aabsent
Exact state: not found · 0 skills
The supported discovery location returned no matching document.
Not found does not prove the service exposes no such interface elsewhere.
Not observed / not fetched
- MCPobserved
Exact state: valid · Revision 2026-07-28 · 16 tools · 1 resource · prompts not advertised
A usable protocol document was retrieved and validated.
Directly observed
- OpenAPIabsent
Exact state: not detected · 0 operations
No endpoint was established from the evidence and scope that InterfaceDelta inspected.
Not detected does not prove that no endpoint exists.
Not observed / not fetched
- WebMCPabsent
Exact state: not detected · 0 declarative form tools · experimental
No named declarative WebMCP form tools were observed in the origin root HTML.
Script-registered tools and other pages are not observed, so this does not mean the site has no WebMCP tools.
Not observed / not fetched
Capabilities
Showing 17 of 17.
| Tool and inputs | ◇ AI reading, beta · confidence | ||||||
|---|---|---|---|---|---|---|---|
| Read as one of the six effects 1 AI only raises attention: these rows come first. | |||||||
| confirmName*, confirmText*, leadId* | Sends messages to people 0.88 | Sends messages to people0.88 | |||||
| |||||||
| Read as none of the six 11 Not a clearance. | |||||||
| campaignId*, confirmPublic*, includeRationale*, leadIds* and 3 more | Creates records0.85 | ||||||
| |||||||
| jobId*, limit | Reads only0.90 | ||||||
| |||||||
| campaignId* | Reads only0.92 | ||||||
| |||||||
| campaignId*, leadIds, limit | Reads only0.90 | ||||||
| |||||||
| campaignId* | Reads only0.94 | ||||||
| |||||||
| leadId* | Reads only0.90 | ||||||
| |||||||
| limit | Reads only0.92 | ||||||
| |||||||
| campaignId | Reads only0.88 | ||||||
| |||||||
| campaignId, limit | Reads only0.90 | ||||||
| |||||||
| campaignId*, limit | Reads only0.90 | ||||||
| |||||||
| leadId*, subject, text* | Changes records0.90 | ||||||
| |||||||
| No counted reading 4 No reading was counted, so any effect is possible. | |||||||
| campaignId*, message*, taskContext | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| limit, query*, taskContext | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| campaignId*, includeRationale*, leadIds*, note* and 1 more | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| id* | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| MCP resources 1 Not read by AI. | |||||||
| no inputs | Not read | ||||||
| |||||||
Read as this effect No reading: unknown Not read as this effect◇ AI readings, beta. A zero is a count, not a clearance.
Not observed in this Passport: A2A skills, MCP prompts, OpenAPI operations.
The atlas shows each capability by its plain identifier, inputs and declared sign-in. Publisher descriptions, paths, links and source evidence are not published here.
The comparison with the previous observation is shown only to the account that recorded it.
Atlas history
1 observation
- 17 capabilities · MCP 2026-07-28 · MCP endpoint validFirst observation
Fingerprint and versions
- Fingerprint
f530a96110cab8b6d7666126b47e437d9b39629761c689ea8cdc384713479573- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: match · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
Each class compares an observation with the previous atlas observation. Runs of unchanged observations are grouped. Struck values are what the previous observation recorded; inserted values are what this one recorded.
Declared and observed
16 tools declare hints; the AI readings agree with all 12 that have a reading.
A disagreement is not a finding about the service: either side can be wrong. How we compare declarations and readings.
About this entry
ai.onsa/onsaListedOfficial MCP Registry · first listed 13 Sep 2026 · last listed 24 Oct 2026
Passive observations of a public interface listed in the Official MCP Registry. An observation does not verify security, ownership or compliance, and InterfaceDelta assigns no scores or rankings. Methodology · Report an inaccuracy · Ask for removal
Identity and snapshot
- Target key
sha256:568f8478de16abbba038b510b3393a07470d8f77e5c493fc92f6e78802db6ce6- Locator SHA-256
a4c62f625e1b4001bf22ba5cfe52466726ce7492df796ce74bbce431f79c7651- Snapshot generated
- 11 Nov 2026, 22:36 UTC
The entry is one exact observed target, not a real-world service identity, and implies no ownership. Endpoint paths are not published; the locator hash lets an operator confirm their own URL.