Atlas entry
agentcosthub.
5 capabilities over MCP. The latest atlas observation recorded a change: breaking.
5 tools. 2 only read. 2 only compute. 1 has 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 5 tools, and 4 have AI readings.
get_model_price and list_models are read as read-only.
get_model_price: Returns a model's API list prices per 1M tokens for input, output and cached input, plus sample monthly agent costs.
list_models: Lists large language models with their API list prices per million tokens, optionally narrowed by provider, search text, or popularity.
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 4 of 5 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 1 tool No reading was counted, so any effect above is possible for it: compare_models.
What changed
The latest atlas observation recorded a change: breaking. 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 | 2025-06-18 · 5 tools · resources not advertised · 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 2025-06-18 · 5 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 5 of 5.
| Tool and inputs | ◇ AI reading, beta · confidence | ||||||
|---|---|---|---|---|---|---|---|
| Read as none of the six 4 Not a clearance. | |||||||
| Estimates monthly costs of AI models for a chatbot, RAG, coding or research workload and lists them cheapest first.cached_percent, calls_per_day, input_tokens, limit and 5 more | Computes only, changes nothing0.84 | ||||||
| |||||||
| Estimates the monthly API spend for a chatbot or AI agent running on a single model, from a preset or from token and call counts.cached_percent, calls_per_day, input_tokens, model* and 4 more | Computes only, changes nothing0.80 | ||||||
| |||||||
| Returns a model's API list prices per 1M tokens for input, output and cached input, plus sample monthly agent costs.model* | Reads only0.90 | ||||||
| |||||||
| Lists large language models with their API list prices per million tokens, optionally narrowed by provider, search text, or popularity.popular_only, provider, search | Reads only0.84 | ||||||
| |||||||
| No counted reading 1 No reading was counted, so any effect is possible. | |||||||
| Shows side-by-side pricing for 2-5 models and, optionally, the estimated monthly cost of one workload.cached_percent, calls_per_day, input_tokens, models* and 4 more | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
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 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
4 observations
- 5 capabilities · MCP 2025-06-18 · MCP endpoint validfingerprint
was 785ebe1465ecnow 6994d61bc56aBreaking- Tool input schema changed:
cheapest_models_for(Breaking) - Tool input schema changed:
compare_models(Breaking) - Tool input schema changed:
estimate_cost(Breaking) - Inventory comparison incomplete:
mcp.streamable-http(Indeterminate)
Fingerprint and versions
- Fingerprint
6994d61bc56abc206de011c6b97909f85c0bda3cefa64291de0693891abce0a6- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
- Tool input schema changed:
- 5 capabilities · MCP 2025-06-18 · MCP endpoint validNo change
Fingerprint and versions
- Fingerprint
785ebe1465eccc01b3135491059d390c801721ad6bec96718384492e9d627bfb- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
- 5 capabilities · MCP 2025-06-18 · MCP endpoint validfingerprint
was d071486fa800now 785ebe1465ecChangedFingerprint and versions
- Fingerprint
785ebe1465eccc01b3135491059d390c801721ad6bec96718384492e9d627bfb- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: not applicable · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
- 5 capabilities · MCP 2025-06-18 · MCP endpoint validFirst observation
Fingerprint and versions
- Fingerprint
d071486fa800675f00fefacd721f1eec4010b1f7b2bb038d8e8c8d620ab0d2c6- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- 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
5 tools declare hints; the AI readings agree with all 4 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.agentcosthub/agent-cost-hubListedOfficial MCP Registry · first listed 2 Nov 2026 · last listed 2 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
sha256:7a7da3ba280841674333ef4712223b51ace15abdedd9446b198a0491ec2d9a1d- Locator SHA-256
a6e2d143fa382fb18a88a93dca5a6dc88994dd1e41fafa76403f76d72d6bc458- Snapshot generated
- 11 Nov 2026, 23:58 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.