How AI is applied across API Evangelist and APIs.io. Read my AI disclosure →
API Evangelist API Evangelist
Discovery
Learnings
Guidance
Toolbox
Alignment
API Evangelist LLC

Cognizant Neuro SAN Agent Service

The HTTP/gRPC/MCP service surface of Neuro SAN (Neuro AI System of Agent Networks), the open-source multi-agent orchestration framework published by Cognizant AI Lab under Apache-2.0. Four operations: list the agent networks a deployment exposes, read a network's function description and private sly_data schemas, inspect its internal connectivity, and hold a streaming conversation with it. The same core is projected three ways - a gRPC service defined in four .proto files, a REST projection generated from those protos via google.api.http annotations and published by the running server at /api/v1/docs, and an MCP 2025-06-18 endpoint that exposes each public agent network as a callable tool. Self-hosted: Cognizant publishes the software, the operator runs the server.

This API exposes 4 operations across 4 paths, organized into 2 resource areas, and defines 16 schemas. It is described by OpenAPI 3.0.3, at version 0.0.1.

Requests are made against the base URL {scheme}://{host}:{port}/api/v1.

4 operations 4 paths 16 schemas 3 GET1 POST

Metadata

The identity and technical contract details declared by the specification.

Specification
OpenAPI 3.0.3
API Version
0.0.1
Base URL
{scheme}://{host}:{port}/api/v1
Resource Areas
2

Paths & Operations 4

Across 4 paths, the API surfaces 4 operations — 3 GET, 1 POST. They span 2 resource areas: ConciergeService, AgentService. Each is listed below with its method, path, parameters, and response codes.

ConciergeService 1

The service provides system-wide information about resources available in current instance of neuro-san.

GET
/api/v1/list
List
ConciergeService_List → 200default
AgentService 3

The service comprises all the exchanges to the backend in support of a single agent's services. Routing is done by way of agent name on the grpc service hosting the agent, so as t…

GET
/api/v1/{agent_name}/connectivity
Connectivity
AgentService_Connectivity 1 param → 200default
GET
/api/v1/{agent_name}/function
Function
AgentService_Function 1 param → 200default
POST
/api/v1/{agent_name}/streaming_chat
StreamingChat
AgentService_StreamingChat 1 param body → 200default

Schemas 16

The contract defines 16 schemas that model the data the API accepts and returns. The most detailed are ChatMessage (8 properties), Function (4 properties), ChatRequest (4 properties), ConnectivityInfo (4 properties). Each schema is shown below with its type and property counts.

AgentInfo
object
Description of an agent's function
3 properties
ChatContext
object
Message for holding the state of play for any chat session such that should the client send this back to the service, a different server knows exactly where to…
1 property
ChatFilter
object
Allows for controlling the messages that get streamed via StreamingChat.
1 property
ChatHistory
object
A structure for storing chat history for a given node in the graph described by the origin.
2 properties
ChatMessage
object
Structure describing a single chat message. This could be a single response, or a list of these might comprise a chat history.
8 properties
ChatRequest
object
Request structure for Chat gRPC method
4 properties
ChatResponse
object
Response structure for Chat gRPC method
2 properties
ConciergeResponse
object
Response structure for List gRPC method
1 property
ConnectivityInfo
object
4 properties
ConnectivityResponse
object
Response structure for Connectivity gRPC method
2 properties
Function
object
Description of an agent's function
4 properties
FunctionResponse
object
Response structure for Function gRPC method
1 property
GoogleProtobufAny
object
Contains an arbitrary serialized message along with a @type that describes the type of the serialized message.
1 property
MimeData
object
A Message identifying image data
2 properties
Origin
object
2 properties
Status
object
The Status type defines a logical error model that is suitable for different programming environments, including REST APIs and RPC APIs. It is used by [gRPC](h…
3 properties

Specification

The full machine-readable OpenAPI contract behind this narrative.

Source

cognizant-technology-neuro-san-agent-service.json Raw ↑
Where this information came from

This is an independent, third-party profile of Cognizant Neuro SAN Agent Service, published by API Evangelist. We do not operate, host, resell, or support these APIs, and we are not affiliated with or endorsed by the company unless stated above. Everything here is built from publicly available information — the company's own site, developer portal, documentation, public repositories, and the specifications it publishes for public use. Nothing is obtained by breaching a system, defeating an access control, or using credentials.

The Kin Score and Agent Readiness rating are independently calculated assessments of a company's public API artifacts, scored against a published rubric. They are not certifications, endorsements, security assessments, or audits.

Corrections, re-scores, and removal are free — no partnership or purchase required, and you do not need to justify the request. A removed company is recorded as unrated, never scored zero for having asked. Acknowledgement within one business day; removal within two.

info@apievangelist.com · Read the full data-sourcing policy →
On a security or compliance team? Put security in the subject line and you will get a person, not a form — we will tell you exactly which public URLs this profile was built from.