Atlas entry
app.
18 capabilities over MCP. First atlas observation.
18 capabilities, 15 of them tools. 15 only read.◇
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 15 have AI readings.
15 tools are read as read-only, including compare_runs, get_battlecard and search_answers.
search_answers: Retrieves stored AI engine answers that mention a given term, returning a short excerpt and receipt ID for each match.
get_sources: Lists the pages that AI answer engines cited in one scheduled-answer run, ranked by citation count and filterable by domain.
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 15 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.
A zero is a count, not a clearance.
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 | Not found | No document retrieved |
|---|---|---|
| A2A | Not found | 0 skills |
| MCP | Valid | 2025-11-25 · 15 tools · 3 resources · 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 2025-11-25 · 15 tools · 3 resources · 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 18 of 18.
| Tool and inputs | ◇ AI reading, beta · confidence | ||||||
|---|---|---|---|---|---|---|---|
| Read as none of the six 15 Not a clearance. | |||||||
| brand_account_id, other_run_id*, run_id* | Reads only0.84 | ||||||
| |||||||
| brand_account_id, competitor, run_id* | Reads only0.90 | ||||||
| |||||||
| Returns competitors named in scheduled answers that left out the client, broken down by question and engine for one run.brand_account_id, limit, offset, question_id and 1 more | Reads only0.90 | ||||||
| |||||||
| No purpose line: the tool declares too little to read.run_id* | Reads only0.90 | ||||||
| |||||||
| brand_account_id, key, scope | Reads only0.89 | ||||||
| |||||||
| Fetches the Index panel published for your saved category; a missing entry does not mean it was measured as absent.no inputs | Reads only0.90 | ||||||
| |||||||
| Returns the method version, its five engines, figure definitions, proof rules, and stated limits on what the numbers prove.brand_account_id | Reads only0.91 | ||||||
| |||||||
| Returns controlled lift experiment results: target and control counts, lift in points, and a fixed verdict for each experiment.brand_account_id, experiment_id, include_superseded | Reads only0.90 | ||||||
| |||||||
| Fetches the details and measured totals for one buyer question, identified by ID within a specified run.question_id*, run_id* | Reads only0.80 | ||||||
| |||||||
| Retrieves saved answers and their cited sources for a single question in a run, five per page.offset, question_id*, run_id* | Reads only0.88 | ||||||
| |||||||
| Fetches the output of a finished measurement run, identified by its run ID.run_id* | Reads only0.90 | ||||||
| |||||||
| Lists the pages that AI answer engines cited in one scheduled-answer run, ranked by citation count and filterable by domain.brand_account_id, domain, limit, offset and 1 more | Reads only0.91 | ||||||
| |||||||
| Lists recent alerts for a brand account where a rate, engine or question type shifted significantly between scheduled runs, newest first.brand_account_id, limit, offset | Reads only0.91 | ||||||
| |||||||
| No purpose line: the tool declares too little to read.no inputs | Reads only0.87 | ||||||
| |||||||
| Retrieves stored AI engine answers that mention a given term, returning a short excerpt and receipt ID for each match.brand_account_id, engine, limit, offset and 3 more | Reads only0.88 | ||||||
| |||||||
| MCP resources 3 Not read by AI. | |||||||
| no inputs | Not read | ||||||
| |||||||
| no inputs | Not read | ||||||
| |||||||
| 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
- 18 capabilities · MCP 2025-11-25 · MCP endpoint validFirst observation
Fingerprint and versions
- Fingerprint
9a073e31e535b3d6bbda587d11aac36581968ef301a74f857a63e86b6470d56c- 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
15 tools declare hints; the AI readings agree with all 15 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
io.github.Broadcastwell/connectorListedOfficial MCP Registry · first listed 4 Nov 2026 · last listed 4 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
sha256:6fa30c180df8017a623ec963f4253f694e45bbca91c455b008f2842530a37001- Locator SHA-256
45f715614fe617278e8f283cecbed7d18f4cac45a3e768b500e85d4e0601153b- Snapshot generated
- 13 Nov 2026, 01:06 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.