CVE-2026-104850 (GCVE-0-2026-104850)
Vulnerability from cvelistv5 – Published: 2026-10-06 16:08 – Updated: 2026-10-06 16:28
VLAI
EPSS
VEX
Title
MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server
Summary
MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. Starting in version 1.12.0 and prior to versions 1.31.0 and 2.2.0, the SDK's OAuth client support let the MCP server a client connected to decide which authorization server received the client's OAuth credentials. Stored and pre-provisioned credentials were not bound to the authorization server they belong to. A malicious or compromised MCP server could name its own authorization server in its protected resource metadata. Without any user interaction, the client would send that server the `refresh_token` and `client_secret` stored from an earlier sign-in (1.x), or the configured `client_secret` or signed assertion of a bundled non-interactive provider (1.x and 2.x). Only those applications that use the SDK as an MCP client over HTTP with an `authProvider`: your own `OAuthClientProvider`, or the bundled `ClientCredentialsProvider`, `PrivateKeyJwtProvider`, `StaticPrivateKeyJwtProvider` or (2.x) `CrossAppAccessProvider` and that may connect to an MCP server the owners does not fully trust while holding credentials for a legitimate authorization server are affected. `@modelcontextprotocol/sdk` 1.31.0 (1.x) and `@modelcontextprotocol/client` 2.2.0 (2.x) patch the issue. A workaround for those who cannot upgrade is available. 2.0.0 and 2.1.0 already accept `expectedIssuer`. On 1.x, the only workaround is to connect OAuth-enabled clients only to MCP servers you trust.
Severity
7.5 (High)
SSVC
Exploitation: none
Automatable: yes
Technical Impact: partial
CISA Coordinator · CISA-ADP (v2.0.3)
Decision recorded 2026-10-06 16:28 UTC
CWE
Assigner
References
4 references
| URL | Tags |
|---|---|
| https://github.com/modelcontextprotocol/typescrip… | x_refsource_CONFIRM |
| https://github.com/modelcontextprotocol/typescrip… | x_refsource_MISC |
| https://github.com/modelcontextprotocol/typescrip… | x_refsource_MISC |
| https://github.com/modelcontextprotocol/typescrip… | x_refsource_MISC |
Impacted products
1 product
| Vendor | Product | Version | CPE status | |
|---|---|---|---|---|
| modelcontextprotocol | typescript-sdk |
Affected:
>= 1.12.0, < 1.31.0
Affected: >= 2.0.0, < 2.2.0 |
guessed |
{
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-104850",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-10-06T16:28:43.638595Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-10-06T16:28:53.097Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "typescript-sdk",
"vendor": "modelcontextprotocol",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.12.0, \u003c 1.31.0"
},
{
"status": "affected",
"version": "\u003e= 2.0.0, \u003c 2.2.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. Starting in version 1.12.0 and prior to versions 1.31.0 and 2.2.0, the SDK\u0027s OAuth client support let the MCP server a client connected to decide which authorization server received the client\u0027s OAuth credentials. Stored and pre-provisioned credentials were not bound to the authorization server they belong to. A malicious or compromised MCP server could name its own authorization server in its protected resource metadata. Without any user interaction, the client would send that server the `refresh_token` and `client_secret` stored from an earlier sign-in (1.x), or the configured `client_secret` or signed assertion of a bundled non-interactive provider (1.x and 2.x). Only those applications that use the SDK as an MCP client over HTTP with an `authProvider`: your own `OAuthClientProvider`, or the bundled `ClientCredentialsProvider`, `PrivateKeyJwtProvider`, `StaticPrivateKeyJwtProvider` or (2.x) `CrossAppAccessProvider` and that may connect to an MCP server the owners does not fully trust while holding credentials for a legitimate authorization server are affected. `@modelcontextprotocol/sdk` 1.31.0 (1.x) and `@modelcontextprotocol/client` 2.2.0 (2.x) patch the issue. A workaround for those who cannot upgrade is available. 2.0.0 and 2.1.0 already accept `expectedIssuer`. On 1.x, the only workaround is to connect OAuth-enabled clients only to MCP servers you trust."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-345",
"description": "CWE-345: Insufficient Verification of Data Authenticity",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-522",
"description": "CWE-522: Insufficiently Protected Credentials",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-06T16:08:21.514Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/security/advisories/GHSA-6qxp-vccf-f47h",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/security/advisories/GHSA-6qxp-vccf-f47h"
},
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/pull/2887",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/pull/2887"
},
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/commit/edd12e282620ebf770d67316f19cf91d4112a1bd",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/commit/edd12e282620ebf770d67316f19cf91d4112a1bd"
},
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/releases/tag/v2.2.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/releases/tag/v2.2.0"
}
],
"source": {
"advisory": "GHSA-6qxp-vccf-f47h",
"discovery": "UNKNOWN"
},
"title": "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-104850",
"datePublished": "2026-10-06T16:08:21.514Z",
"dateReserved": "2026-10-02T14:38:43.244Z",
"dateUpdated": "2026-10-06T16:28:53.097Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2",
"vulnerability-lookup:meta": {
"nvd": {
"cve": {
"affected": [
{
"affectedData": [
{
"product": "typescript-sdk",
"vendor": "modelcontextprotocol",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.12.0, \u003c 1.31.0"
},
{
"status": "affected",
"version": "\u003e= 2.0.0, \u003c 2.2.0"
}
]
}
],
"source": "security-advisories@github.com"
}
],
"cveTags": [],
"descriptions": [
{
"lang": "en",
"value": "MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. Starting in version 1.12.0 and prior to versions 1.31.0 and 2.2.0, the SDK\u0027s OAuth client support let the MCP server a client connected to decide which authorization server received the client\u0027s OAuth credentials. Stored and pre-provisioned credentials were not bound to the authorization server they belong to. A malicious or compromised MCP server could name its own authorization server in its protected resource metadata. Without any user interaction, the client would send that server the `refresh_token` and `client_secret` stored from an earlier sign-in (1.x), or the configured `client_secret` or signed assertion of a bundled non-interactive provider (1.x and 2.x). Only those applications that use the SDK as an MCP client over HTTP with an `authProvider`: your own `OAuthClientProvider`, or the bundled `ClientCredentialsProvider`, `PrivateKeyJwtProvider`, `StaticPrivateKeyJwtProvider` or (2.x) `CrossAppAccessProvider` and that may connect to an MCP server the owners does not fully trust while holding credentials for a legitimate authorization server are affected. `@modelcontextprotocol/sdk` 1.31.0 (1.x) and `@modelcontextprotocol/client` 2.2.0 (2.x) patch the issue. A workaround for those who cannot upgrade is available. 2.0.0 and 2.1.0 already accept `expectedIssuer`. On 1.x, the only workaround is to connect OAuth-enabled clients only to MCP servers you trust."
}
],
"id": "CVE-2026-104850",
"lastModified": "2026-10-06T20:03:40.690",
"metrics": {
"cvssMetricV31": [
{
"cvssData": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
},
"exploitabilityScore": 3.9,
"impactScore": 3.6,
"source": "security-advisories@github.com",
"type": "Secondary"
}
],
"ssvcV203": [
{
"source": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"ssvcData": {
"id": "CVE-2026-104850",
"options": [
{
"exploitation": "none"
},
{
"automatable": "yes"
},
{
"technicalImpact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-10-06T16:28:43.638595Z",
"version": "2.0.3"
}
}
]
},
"published": "2026-10-06T17:17:15.827",
"references": [
{
"source": "security-advisories@github.com",
"url": "https://github.com/modelcontextprotocol/typescript-sdk/commit/edd12e282620ebf770d67316f19cf91d4112a1bd"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/modelcontextprotocol/typescript-sdk/pull/2887"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/modelcontextprotocol/typescript-sdk/releases/tag/v2.2.0"
},
{
"source": "security-advisories@github.com",
"url": "https://github.com/modelcontextprotocol/typescript-sdk/security/advisories/GHSA-6qxp-vccf-f47h"
}
],
"sourceIdentifier": "security-advisories@github.com",
"vulnStatus": "Awaiting Analysis",
"weaknesses": [
{
"description": [
{
"lang": "en",
"value": "CWE-345"
},
{
"lang": "en",
"value": "CWE-522"
}
],
"source": "security-advisories@github.com",
"type": "Primary"
}
]
}
},
"vulnrichment": {
"containers": {
"adp": [
{
"metrics": [
{
"other": {
"content": {
"id": "CVE-2026-104850",
"options": [
{
"Exploitation": "none"
},
{
"Automatable": "yes"
},
{
"Technical Impact": "partial"
}
],
"role": "CISA Coordinator",
"timestamp": "2026-10-06T16:28:43.638595Z",
"version": "2.0.3"
},
"type": "ssvc"
}
}
],
"providerMetadata": {
"dateUpdated": "2026-10-06T16:28:48.282Z",
"orgId": "134c704f-9b21-4f2e-91b3-4a467353bcc0",
"shortName": "CISA-ADP"
},
"title": "CISA ADP Vulnrichment"
}
],
"cna": {
"affected": [
{
"product": "typescript-sdk",
"vendor": "modelcontextprotocol",
"versions": [
{
"status": "affected",
"version": "\u003e= 1.12.0, \u003c 1.31.0"
},
{
"status": "affected",
"version": "\u003e= 2.0.0, \u003c 2.2.0"
}
]
}
],
"descriptions": [
{
"lang": "en",
"value": "MCP TypeScript SDK is the official TypeScript SDK for Model Context Protocol servers and clients. Starting in version 1.12.0 and prior to versions 1.31.0 and 2.2.0, the SDK\u0027s OAuth client support let the MCP server a client connected to decide which authorization server received the client\u0027s OAuth credentials. Stored and pre-provisioned credentials were not bound to the authorization server they belong to. A malicious or compromised MCP server could name its own authorization server in its protected resource metadata. Without any user interaction, the client would send that server the `refresh_token` and `client_secret` stored from an earlier sign-in (1.x), or the configured `client_secret` or signed assertion of a bundled non-interactive provider (1.x and 2.x). Only those applications that use the SDK as an MCP client over HTTP with an `authProvider`: your own `OAuthClientProvider`, or the bundled `ClientCredentialsProvider`, `PrivateKeyJwtProvider`, `StaticPrivateKeyJwtProvider` or (2.x) `CrossAppAccessProvider` and that may connect to an MCP server the owners does not fully trust while holding credentials for a legitimate authorization server are affected. `@modelcontextprotocol/sdk` 1.31.0 (1.x) and `@modelcontextprotocol/client` 2.2.0 (2.x) patch the issue. A workaround for those who cannot upgrade is available. 2.0.0 and 2.1.0 already accept `expectedIssuer`. On 1.x, the only workaround is to connect OAuth-enabled clients only to MCP servers you trust."
}
],
"metrics": [
{
"cvssV3_1": {
"attackComplexity": "LOW",
"attackVector": "NETWORK",
"availabilityImpact": "NONE",
"baseScore": 7.5,
"baseSeverity": "HIGH",
"confidentialityImpact": "HIGH",
"integrityImpact": "NONE",
"privilegesRequired": "NONE",
"scope": "UNCHANGED",
"userInteraction": "NONE",
"vectorString": "CVSS:3.1/AV:N/AC:L/PR:N/UI:N/S:U/C:H/I:N/A:N",
"version": "3.1"
}
}
],
"problemTypes": [
{
"descriptions": [
{
"cweId": "CWE-345",
"description": "CWE-345: Insufficient Verification of Data Authenticity",
"lang": "en",
"type": "CWE"
}
]
},
{
"descriptions": [
{
"cweId": "CWE-522",
"description": "CWE-522: Insufficiently Protected Credentials",
"lang": "en",
"type": "CWE"
}
]
}
],
"providerMetadata": {
"dateUpdated": "2026-10-06T16:08:21.514Z",
"orgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"shortName": "GitHub_M"
},
"references": [
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/security/advisories/GHSA-6qxp-vccf-f47h",
"tags": [
"x_refsource_CONFIRM"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/security/advisories/GHSA-6qxp-vccf-f47h"
},
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/pull/2887",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/pull/2887"
},
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/commit/edd12e282620ebf770d67316f19cf91d4112a1bd",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/commit/edd12e282620ebf770d67316f19cf91d4112a1bd"
},
{
"name": "https://github.com/modelcontextprotocol/typescript-sdk/releases/tag/v2.2.0",
"tags": [
"x_refsource_MISC"
],
"url": "https://github.com/modelcontextprotocol/typescript-sdk/releases/tag/v2.2.0"
}
],
"source": {
"advisory": "GHSA-6qxp-vccf-f47h",
"discovery": "UNKNOWN"
},
"title": "MCP TypeScript SDK: OAuth client could send credentials to an authorization server chosen by the MCP server"
}
},
"cveMetadata": {
"assignerOrgId": "a0819718-46f1-4df5-94e2-005712e83aaa",
"assignerShortName": "GitHub_M",
"cveId": "CVE-2026-104850",
"datePublished": "2026-10-06T16:08:21.514Z",
"dateReserved": "2026-10-02T14:38:43.244Z",
"dateUpdated": "2026-10-06T16:28:53.097Z",
"state": "PUBLISHED"
},
"dataType": "CVE_RECORD",
"dataVersion": "5.2"
}
}
}
Loading…
Loading…
Experimental. This forecast is provided for visualization only and may change without notice. Do not use it for operational decisions.
Forecast uses a logistic model when the trend is rising, or an exponential decay model when the trend is falling. Fitted via linearized least squares.
Sightings
| Author | Source | Type | Date | Other |
|---|
Nomenclature
- Seen: The vulnerability was mentioned, discussed, or observed by the user.
- Confirmed: The vulnerability has been validated from an analyst's perspective.
- Published Proof of Concept: A public proof of concept is available for this vulnerability.
- Exploited: The vulnerability was observed as exploited by the user who reported the sighting.
- Patched: The vulnerability was observed as successfully patched by the user who reported the sighting.
- Not exploited: The vulnerability was not observed as exploited by the user who reported the sighting.
- Not confirmed: The user expressed doubt about the validity of the vulnerability.
- Not patched: The vulnerability was not observed as successfully patched by the user who reported the sighting.
Loading…
Loading…
The MITRE ATT&CK techniques below are AI-generated suggestions, inferred from the description of the
vulnerability by the CIRCL/vulnerability-attack-technique-classification-roberta-base
model, served locally by ML-Gateway.
They have not been verified by an analyst and are provided for guidance only.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
The approach is described in our paper Mapping CVEs to MITRE ATT&CK Techniques: A Curated Gold-Set Classifier and the Limits of LLM-Assisted Label Expansion.
Browse all ATT&CK techniques and the vulnerabilities related to each.
Loading…
Related by attack behaviour
Vulnerabilities whose description is nearest to this one in the vector space of the CIRCL/vulnerability-attack-technique-biencoder model. This is a similarity search over the bi-encoder space (plain cosine), not a classification, and it has no measured accuracy.
Loading…