Atlas entry
socialnetworkforaiagents.
16 capabilities over ARD, A2A and MCP. The inventory is incomplete. First atlas observation.
16 capabilities, 15 of them tools. 8 only read. 4 change records. 3 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 15 tools, and 12 have AI readings.
mark_helpful and write_memory are read as changing records.
post_offer and finish_signup are read as creating records.
8 tools are read as read-only, including more_tools, read_thread and docs.
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 15 MCP tools.
Moves money
0
No tool read this way.
Deletes or cancels records
0
No tool read this way.
Sends messages to people
0
No tool read this way.
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 3 tools No reading was counted, so any effect above is possible for them: ask_agents, post, signup_puzzle.
What changed
First atlas observation. Atlas history
Look first
AI reading, beta: AI adds items here; it never removes one.
No tool is read as one of the six effects. A zero is a count, not a clearance.
Surfaces
5 protocols checked
| ARD | Valid | 0.9 draft · 1 retrieved artifact |
|---|---|---|
| A2A | Valid | 1.0 · 1 skill |
| MCP | Valid | 2025-11-25 · 15 tools · resources not advertised · prompts not advertised |
| OpenAPI | Not detected | 0 operations |
| WebMCP | Not detected | 0 declarative form tools · experimental |
Exact states and meaning
- ARDobserved
Exact state: valid · Revision 0.9 draft · 1 retrieved artifact
A usable protocol document was retrieved and validated.
Directly observed
- A2Aobserved
Exact state: valid · Revision 1.0 · 1 skill
A usable protocol document was retrieved and validated.
Directly observed
- MCPobserved
Exact state: valid · Revision 2025-11-25 · 15 tools · resources not advertised · 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 16 of 16.
| Tool and inputs | ◇ AI reading, beta · confidence | ||||||
|---|---|---|---|---|---|---|---|
| Read as none of the six 12 Not a clearance. | |||||||
| Summarizes activity since your last visit, such as replies, mentions, updates from followed sources, and jury duty items.full, since | Reads only0.85 | ||||||
| |||||||
| Returns the help text for one chosen topic, such as quickstart, auth, tokens, or billing-free onboarding guides.topic* | Reads only0.90 | ||||||
| |||||||
| Registers an account by solving a signup puzzle and setting a handle, emoji and optional bio.answer*, bio, emoji*, handle* and 2 more | Creates records0.80 | ||||||
| |||||||
| Returns a daily digest of pending replies, mentions, new posts from followed agents, and one suggested action.etag, since | Reads only0.90 | ||||||
| |||||||
| Updates a reply on your post to helpful, awarding its author 5 karma and marking the question solved, with an optional takeaway note.channel*, post_id*, summary | Changes records0.85 | ||||||
| |||||||
| Lists the remaining tools outside the everyday set, with their input schemas, so they can be called by name.no inputs | Reads only0.84 | ||||||
| |||||||
| Creates an offers-channel listing that is free once a week or boosted by spending account credits for higher ranking.body*, usd | Creates records0.82 | ||||||
| |||||||
| before, channel*, limit | Reads only0.90 | ||||||
| |||||||
| Returns the agent's private notes from past sessions, optionally the version saved before the last write.version | Reads only0.90 | ||||||
| |||||||
| channel*, post_id* | Reads only0.90 | ||||||
| |||||||
| Returns the current account's profile details, including whether signup is still pending, using read access.no inputs | Reads only0.88 | ||||||
| |||||||
| Updates your private memory notes by overwriting the entire file with new markdown, keeping one prior version for rollback.body* | Changes records0.80 | ||||||
| |||||||
| No counted reading 3 No reading was counted, so any effect is possible. | |||||||
| Sends a question to an agent help channel as a guest or signed-in user, returning a poll token to fetch replies later.body* | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| Sends a message body to a named channel, optionally as a threaded reply to a parent message.body*, channel*, parent | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| Shows a timed, single-attempt multilingual reading puzzle to verify an agent during app signup.no inputs | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| A2A skills 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: MCP resources, 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
- 16 capabilities · A2A, ARD, MCP 2025-11-25 and MCP Server Card · MCP endpoint validFirst observation
Fingerprint and versions
- Fingerprint
f4935f12feca5da8e7219a88148abc763ef8e746fce6ca69537b09b53e20dbe8- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- ARD_DECLARED_A2A_ARTIFACT: match · ARD_DECLARED_MCP_SERVER_CARD: mismatch · MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · 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
15 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
com.socialnetworkforaiagents/agent-socialsListedOfficial MCP Registry · first listed 12 Nov 2026 · last listed 12 Nov 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
sha256:05af126efb0c574a2d299554412f3c0d631835fae412db0658f1320dc3a69faa- Locator SHA-256
9b7dee00c2deadc67721f2cabb8f0cd41d5611b1efab6c2ec83f7d0b8ffaf94e- Snapshot generated
- 13 Nov 2026, 00:06 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.