Atlas entry
mcp.
7 capabilities over MCP. The inventory is incomplete. The latest atlas observation recorded a change: indeterminate.
7 capabilities, 6 of them tools. 1 only reads. 1 changes records. 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 6 tools, and 2 have AI readings.
corpusfetch_request_experience is read as creating records.
corpusfetch_search is read as read-only.
corpusfetch_lookup_exception: Returns verified operational guidance for a named Python exception class to inform error-handling choices.
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 2 of 6 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 4 tools No reading was counted, so any effect above is possible for them: corpusfetch_fetch_record, corpusfetch_fetch_warrant, corpusfetch_lookup_exception, corpusfetch_lookup_symptom.
What changed
The latest atlas observation recorded a change: indeterminate. 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 | invalid | 1 retrieved artifact |
|---|---|---|
| A2A | invalid | 0 skills |
| MCP | Valid | 2025-06-18 · 6 tools · resources not advertised · 1 prompt |
| OpenAPI | Not detected | 0 operations |
| WebMCP | Not detected | 0 declarative form tools · experimental |
Exact states and meaning
- ARDfailed
Exact state: invalid · Revision v0.91 · 1 retrieved artifact
InterfaceDelta retained the machine state “invalid” without assigning an additional meaning.
Not observed / not fetched
- A2Afailed
Exact state: invalid · Revision 1.0 · 0 skills
InterfaceDelta retained the machine state “invalid” without assigning an additional meaning.
Not observed / not fetched
- MCPobserved
Exact state: valid · Revision 2025-06-18 · 6 tools · resources not advertised · 1 prompt
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 7 of 7.
| Tool and inputs | ◇ AI reading, beta · confidence | ||||||
|---|---|---|---|---|---|---|---|
| Read as none of the six 2 Not a clearance. | |||||||
| Starts generating a new troubleshooting record for a novel error or symptom, publishing it to the corpus within a few minutes.query* | Creates records0.85 | ||||||
| |||||||
| Retrieves empirically recorded failure modes matching a text query across infrastructure, agent protocols, databases and concurrency.query* | Reads only0.85 | ||||||
| |||||||
| No counted reading 4 No reading was counted, so any effect is possible. | |||||||
| Retrieves a stored experience record by slug, as markdown with reasoning or as compact executable invariants.format, slug* | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| Fetches a short validity check for a record identified by slug, to confirm it applies before loading the full record.slug* | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| Returns verified operational guidance for a named Python exception class to inform error-handling choices.exception_class* | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| Returns stored operational notes on a named runtime symptom or boundary failure when a failure state is unclear.symptom* | unknown | unknown | unknown | unknown | unknown | unknown | No reading |
| |||||||
| MCP prompts 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.
A2A skills 0+ observed
Inventory incomplete. The displayed count is a lower bound; missing items do not prove removal.
None recorded in this Passport.
MCP resources 0+ observed
Inventory incomplete. MCP resources could not be fully inventoried: the ARD document was not valid, so declarations made there were not read.
None recorded in this Passport.
OpenAPI operations 0+ observed
Inventory incomplete. OpenAPI operations could not be fully inventoried: the ARD document was not valid, so declarations made there were not read.
None recorded in this Passport.
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
- 7 capabilities · MCP 2025-06-18 · MCP endpoint validfingerprint
was 435be4119d1dnow 329c05495054Indeterminate- Inventory comparison incomplete:
mcp.streamable-http(Indeterminate)
1 informational changes
Fingerprint and versions
- Fingerprint
329c0549505469b9aaeb7db3c045f9c6b143302bf6619aa1659876c9ecafb401- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: match · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
- Inventory comparison incomplete:
- 7 capabilities · MCP 2025-06-18 · MCP endpoint validfingerprint
was 08c6e7843451now 435be4119d1dIndeterminate- Inventory comparison incomplete:
mcp.streamable-http(Indeterminate)
6 informational changes
Fingerprint and versions
- Fingerprint
435be4119d1d212b7c4001eada34564f8604b2ef196504067b8e60a674e77cba- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: match · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
- Inventory comparison incomplete:
- 7 capabilities · MCP 2025-06-18 · MCP endpoint valid
was 4now 7 capabilitiesChangedFingerprint and versions
- Fingerprint
08c6e7843451290f9cbc41cb9ad52b177eae88e363d2078f895430a21528ce58- Passport schema
- 0.5.0, passport-semantic-v4
- Consistency
- MCP_PROMPTS_ADVERTISEMENT_LIST: match · MCP_RESOURCES_ADVERTISEMENT_LIST: not applicable · MCP_TOOLS_ADVERTISEMENT_LIST: match · OPENAPI_MCP_EXPLICIT_MAPPING: not applicable
- 4 capabilities · MCP 2025-06-18 · MCP endpoint validFirst observation
Fingerprint and versions
- Fingerprint
4012e0021385da76cdd0015703c9f5638262e84ad762edcc3e8240f048c3ffe7- 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
No tools declare hints.
A disagreement is not a finding about the service: either side can be wrong. How we compare declarations and readings.
About this entry
com.corpusfetch/corpusfetchListedOfficial 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
sha256:5f2b9d111ef94967f6da404942c5657e25e3f41210f27953411bb66b1db7fa5a- Locator SHA-256
6f36e128d6a88d8645c681c5be482207809174cb417cf24b32aa78f96faf0e38- Snapshot generated
- 12 Nov 2026, 01:19 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.