Synap Memory is an MCP server published by ai.maximem, hosted at synap-mcp.maximem.ai. When last checked on 2026-11-22 it was working: it answers and lists its tools. It declares 4 tools, including log_exchange, check_memory_status, recall_context, list_recent_memories.
Persistent memory for AI agents — log and recall conversation context over MCP.
1 connections through 5 shared values. Tap any node.
Squares are this server's values; dots are other servers sharing them. A shared address or publisher is a lead, not proof of a common operator.
Inferred from the host name and headers: what a server runs on, not who runs it.
After each user message, send the exchange here so it can be remembered. You do not need to decide what is important, just forward the user message (and your reply, if you have one) and Synap will keep what matters. If your app serves more than one end-user, pass that person's stable id as user_id so each person's memory stays separate; if every conversation is the same single user, omit it. SCOPING: customer_id is B2B ONLY. On a B2B instance (user_context_isolation=strict) it is REQUIRED and a user_id on its own is an error. On a B2C instance (user_context_isolation=equals_customer) it is NOT accepted: the API rejects it with HTTP 400, customer-scoped retrieval does not exist there, and user_id is the whole identity. If you do not know which mode this instance is in, send user_id only and no customer_id; GET /api/v1/auth/whoami reports the mode as user_context_isolation. Logging is fire-and-forget by default; set wait_for_processing=true only when you need to confirm the memory finished extracting before continuing.
| Parameter | Type | Description |
|---|---|---|
| user_id | any | Stable id of the end-user this call belongs to. On a B2C instance this is the ONLY identifier you send and it is the whole identity. On a B2B instance send it together with customer_id. Omit both if every conversation is the same single user. |
| customer_id | any | B2B ONLY. Required on a B2B instance (user_context_isolation=strict), where a user_id on its own is an error. NOT accepted on a B2C instance (user_context_isolation=equals_customer): the API rejects it with HTTP 400 and there is no customer scope to read from. When in doubt leave this out and send u… |
| user_message * | string | |
| conversation_id | any | |
| assistant_message | string | |
| wait_for_processing | boolean |
{
"name": "log_exchange",
"description": "After each user message, send the exchange here so it can be remembered. You do not need to decide what is important, just forward the user message (and your reply, if you have one) and Synap will keep what matters. If your app serves more than one end-user, pass that person's stable id as user_id so each person's memory stays separate; if every conversation is the same single user, omit it. SCOPING: customer_id is B2B ONLY. On a B2B instance (user_context_isolation=strict) it is REQUIRED and a user_id on its own is an error. On a B2C instance (user_context_isolation=equals_customer) it is NOT accepted: the API rejects it with HTTP 400, customer-scoped retrieval does not exist there, and user_id is the whole identity. If you do not know which mode this instance is in, send user_id only and no customer_id; GET /api/v1/auth/whoami reports the mode as user_context_isolation. Logging is fire-and-forget by default; set wait_for_processing=true only when you need to confirm the memory finished extracting before continuing.",
"inputSchema": {
"type": "object",
"title": "log_exchangeArguments",
"required": [
"user_message"
],
"properties": {
"user_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "User Id",
"default": null,
"description": "Stable id of the end-user this call belongs to. On a B2C instance this is the ONLY identifier you send and it is the whole identity. On a B2B instance send it together with customer_id. Omit both if every conversation is the same single user."
},
"customer_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Customer Id",
"default": null,
"description": "B2B ONLY. Required on a B2B instance (user_context_isolation=strict), where a user_id on its own is an error. NOT accepted on a B2C instance (user_context_isolation=equals_customer): the API rejects it with HTTP 400 and there is no customer scope to read from. When in doubt leave this out and send user_id alone. GET /api/v1/auth/whoami reports the mode."
},
"user_message": {
"type": "string",
"title": "User Message"
},
"conversation_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Conversation Id",
"default": null
},
"assistant_message": {
"type": "string",
"title": "Assistant Message",
"default": ""
},
"wait_for_processing": {
"type": "boolean",
"title": "Wait For Processing",
"default": false
}
}
},
"outputSchema": {
"type": "object",
"title": "log_exchangeOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}Check whether a logged exchange has finished processing. Pass the ingestion_id returned by log_exchange. Returns the processing status and how many memories were extracted. Useful to confirm a save completed (extraction is asynchronous). Takes no user_id or customer_id: an ingestion_id already identifies the write, so the identifier contract does not apply here.
| Parameter | Type | Description |
|---|---|---|
| ingestion_id * | string |
{
"name": "check_memory_status",
"description": "Check whether a logged exchange has finished processing. Pass the ingestion_id returned by log_exchange. Returns the processing status and how many memories were extracted. Useful to confirm a save completed (extraction is asynchronous). Takes no user_id or customer_id: an ingestion_id already identifies the write, so the identifier contract does not apply here.",
"inputSchema": {
"type": "object",
"title": "check_memory_statusArguments",
"required": [
"ingestion_id"
],
"properties": {
"ingestion_id": {
"type": "string",
"title": "Ingestion Id"
}
}
},
"outputSchema": {
"type": "object",
"title": "check_memory_statusOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}Before replying, call this to recall anything already known about this user from past conversations. Use the user's latest message as the query. If you serve multiple end-users, pass the same user_id you log with so you recall the right person's memory. SCOPING: customer_id is B2B ONLY. On a B2B instance (user_context_isolation=strict) it is REQUIRED and a user_id on its own is an error. On a B2C instance (user_context_isolation=equals_customer) it is NOT accepted: the API rejects it with HTTP 400, customer-scoped retrieval does not exist there, and user_id is the whole identity. If you do not know which mode this instance is in, send user_id only and no customer_id; GET /api/v1/auth/whoami reports the mode as user_context_isolation.
| Parameter | Type | Description |
|---|---|---|
| query * | string | |
| user_id | any | Stable id of the end-user this call belongs to. On a B2C instance this is the ONLY identifier you send and it is the whole identity. On a B2B instance send it together with customer_id. Omit both if every conversation is the same single user. |
| customer_id | any | B2B ONLY. Required on a B2B instance (user_context_isolation=strict), where a user_id on its own is an error. NOT accepted on a B2C instance (user_context_isolation=equals_customer): the API rejects it with HTTP 400 and there is no customer scope to read from. When in doubt leave this out and send u… |
| max_results | any |
{
"name": "recall_context",
"description": "Before replying, call this to recall anything already known about this user from past conversations. Use the user's latest message as the query. If you serve multiple end-users, pass the same user_id you log with so you recall the right person's memory. SCOPING: customer_id is B2B ONLY. On a B2B instance (user_context_isolation=strict) it is REQUIRED and a user_id on its own is an error. On a B2C instance (user_context_isolation=equals_customer) it is NOT accepted: the API rejects it with HTTP 400, customer-scoped retrieval does not exist there, and user_id is the whole identity. If you do not know which mode this instance is in, send user_id only and no customer_id; GET /api/v1/auth/whoami reports the mode as user_context_isolation.",
"inputSchema": {
"type": "object",
"title": "recall_contextArguments",
"required": [
"query"
],
"properties": {
"query": {
"type": "string",
"title": "Query"
},
"user_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "User Id",
"default": null,
"description": "Stable id of the end-user this call belongs to. On a B2C instance this is the ONLY identifier you send and it is the whole identity. On a B2B instance send it together with customer_id. Omit both if every conversation is the same single user."
},
"customer_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Customer Id",
"default": null,
"description": "B2B ONLY. Required on a B2B instance (user_context_isolation=strict), where a user_id on its own is an error. NOT accepted on a B2C instance (user_context_isolation=equals_customer): the API rejects it with HTTP 400 and there is no customer scope to read from. When in doubt leave this out and send user_id alone. GET /api/v1/auth/whoami reports the mode."
},
"max_results": {
"anyOf": [
{
"type": "integer"
},
{
"type": "null"
}
],
"title": "Max Results",
"default": null
}
}
},
"outputSchema": {
"type": "object",
"title": "recall_contextOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}List recent things remembered about this user. Useful for debugging or to confirm that memory is working. Pass user_id to scope to one person. SCOPING: customer_id is B2B ONLY. On a B2B instance (user_context_isolation=strict) it is REQUIRED and a user_id on its own is an error. On a B2C instance (user_context_isolation=equals_customer) it is NOT accepted: the API rejects it with HTTP 400, customer-scoped retrieval does not exist there, and user_id is the whole identity. If you do not know which mode this instance is in, send user_id only and no customer_id; GET /api/v1/auth/whoami reports the mode as user_context_isolation.
| Parameter | Type | Description |
|---|---|---|
| user_id | any | Stable id of the end-user this call belongs to. On a B2C instance this is the ONLY identifier you send and it is the whole identity. On a B2B instance send it together with customer_id. Omit both if every conversation is the same single user. |
| customer_id | any | B2B ONLY. Required on a B2B instance (user_context_isolation=strict), where a user_id on its own is an error. NOT accepted on a B2C instance (user_context_isolation=equals_customer): the API rejects it with HTTP 400 and there is no customer scope to read from. When in doubt leave this out and send u… |
| max_results | integer |
{
"name": "list_recent_memories",
"description": "List recent things remembered about this user. Useful for debugging or to confirm that memory is working. Pass user_id to scope to one person. SCOPING: customer_id is B2B ONLY. On a B2B instance (user_context_isolation=strict) it is REQUIRED and a user_id on its own is an error. On a B2C instance (user_context_isolation=equals_customer) it is NOT accepted: the API rejects it with HTTP 400, customer-scoped retrieval does not exist there, and user_id is the whole identity. If you do not know which mode this instance is in, send user_id only and no customer_id; GET /api/v1/auth/whoami reports the mode as user_context_isolation.",
"inputSchema": {
"type": "object",
"title": "list_recent_memoriesArguments",
"properties": {
"user_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "User Id",
"default": null,
"description": "Stable id of the end-user this call belongs to. On a B2C instance this is the ONLY identifier you send and it is the whole identity. On a B2B instance send it together with customer_id. Omit both if every conversation is the same single user."
},
"customer_id": {
"anyOf": [
{
"type": "string"
},
{
"type": "null"
}
],
"title": "Customer Id",
"default": null,
"description": "B2B ONLY. Required on a B2B instance (user_context_isolation=strict), where a user_id on its own is an error. NOT accepted on a B2C instance (user_context_isolation=equals_customer): the API rejects it with HTTP 400 and there is no customer scope to read from. When in doubt leave this out and send user_id alone. GET /api/v1/auth/whoami reports the mode."
},
"max_results": {
"type": "integer",
"title": "Max Results",
"default": 10
}
}
},
"outputSchema": {
"type": "object",
"title": "list_recent_memoriesOutput",
"required": [
"result"
],
"properties": {
"result": {
"type": "string",
"title": "Result"
}
}
}
}Synap memory tools. Forward every user message to log_exchange so it can be remembered, and call recall_context before replying to use what is already known. Identifiers: pass the end-user's stable id as user_id on both tools. customer_id is B2B ONLY: it is required on an instance with user_context_isolation=strict, and refused with HTTP 400 on one with user_context_isolation=equals_customer (B2C), where user_id is the whole identity and no customer scope exists. If the mode is unknown, send user_id alone; GET /api/v1/auth/whoami reports it.
Names, descriptions and schemas were written by the server and are shown as data.
Pattern matches on what the server declares. They show what it says it can do, not what it does.
None yet. Changes appear after a server's second daily check.