CVE-2025-49596

CRITICALNVD 9.49.4
EchelonGraph scoreMEDIUM confidence

“—” beside the score: it is equal to NVD's CVSS score.

This critical-severity CVE scores 9.4 under NVD CVSS. EPSS exploit probability: 40% (98th percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from NVD CVSS
Sources: EPSS, NVD CVSS
Elevated

Also known asEUVD-2025-20870 (ENISA EUVD) · GHSA-7f8r-222p-6f5g (GitHub Security Advisories)Source: ENISA EUVD

9.4EG
EchelonGraph verdictPlan a fixRemediate within your standard update timelines (the SSVC decision on this page).
  • High severity, but no confirmed exploitation yet
CISA-KEV: Not listedEPSS PROB: 40%CVSS: 9.4Exploit: No code on recordExposed services: Not assessed

A fix is available — apply it.

The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to launch MCP commands over stdio. Users should immediately upgrade to version 0.14.1 or later to address these vulnerabilities.

CVSS
9.4
EG Score
9.4CRITICALmedium confidence
EG Risk
58
EG Risk 58/100

EG Risk is EchelonGraph's 0–100 priority score. It fuses impact severity (EG Severity, the CVSS base score, never the KEV-floored or EPSS-lifted EG Score) with real-world exploitation and automatability, under weights EchelonGraph set by hand, so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner.

How it’s computed (value × EchelonGraph’s weight)
Severity94% × 45%
Impact severity (EG Severity): CVSS 9.4 of 10. Never the KEV-floored or EPSS-lifted EG Score.
Exploitation40% × 40%
EchelonGraph's fixed weight for EG-KEV Tier 3 (Elevated): a constant, not a probability.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at low or medium mission impact; Track* at high (mission-essential systems).
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE.
Action: A fix is available. Apply it within your standard update timelines.
EPSS PROB
40%
EPSS %ILE
98th
KEV
Not listed

What the EG score is made of (scorer v4.0: the three questions the 0–10 score mixes, published apart · methodology)

The EG score (9.4): severity, escalated by confirmed exploitation. This CVE's 9.4 is its impact severity (EG Severity), not escalated.

EG Severity
9.4 CRITICALCVSS-B, impact only: no KEV listing, EPSS or EG-KEV tier raises it.NVD CVSS
EG Likelihood
40% within 30 daysSource: FIRST EPSS (model v2026.06.15, score date 2026-11-12). FIRST's exploitation probability, not an EchelonGraph model.
Confirmed exploitation
None on record (CISA KEV, EG-KEV Tier 1)Reported apart from the likelihood: an observed fact, not a probability.
EG Priority
SSVC Track at medium mission impactTrack at low or medium mission impact; Track* at high (mission-essential systems).CISA BOD 26-04: 14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.Each input and its source, and whom BOD 26-04 binds: the SSVC and BOD 26-04 blocks below.

SSVC (CISA's decision table, applied by EchelonGraph)Track at low or medium mission impact; Track* at high (mission-essential systems).

A fix is available. Apply it within your standard update timelines.

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). All three are CISA's SSVC values (Vulnrichment). EchelonGraph applied CISA's decision table to them; CISA publishes SSVC inputs and the table, not a decision for each CVE. Mission impact is CISA's Mission & Well-being decision point, and only you can judge it. CISA's table makes it high when Mission Prevalence is Essential — the vulnerable component "directly provides capabilities that constitute at least one MEF for at least one entity" (MEF: mission essential function) — or when Public Well-Being Impact is Irreversible: "multiple fatalities are likely", the cyber-physical system "is likely lost or destroyed", "extreme or serious externalities" are imposed on other parties, or social systems such as elections or the financial grid "are destabilized and potentially collapse". CISA's decision table

BOD 26-04 (CISA's remediation timeline, Table 1)14 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

The score's inputs: In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact total (CISA Vulnrichment). Whether your system is publicly exposed is yours to answer. BOD 26-04 binds US Federal Civilian Executive Branch agencies; for anyone else it is CISA's published timeline, a reference rather than an obligation. The directive · how EchelonGraph applies it

Published

June 13, 2025

Last Modified

April 15, 2026

Advisory Details (4)

Auto-updated Oct 2, 2026
Patch available. Sources: github, github_commit.
Web page

Critical RCE in Anthropic MCP Inspector (CVE-2025-49596) Enables Browser-Based Exploits

https://www.oligo.security/blog/critical-rce-vulnerability-in-anthropic-mcp-inspector-cve-2025-49596
Web page

MCP Vulnerability Exposes the AI Untrusted Code Crisis - The New Stack

https://thenewstack.io/mcp-vulnerability-exposes-the-ai-untrusted-code-crisis
GitHub advisoryMentions a patch (unverified)

Inspector proxy server vulnerabilities · Advisory · modelcontextprotocol/inspector · GitHub

https://github.com/modelcontextprotocol/inspector/security/advisories/GHSA-7f8r-222p-6f5g
GitHub commit Patch Available

commit 50df0e1ec488 (modelcontextprotocol/inspector)

Patch available: modelcontextprotocol/inspector 0.16.8 (contains commit 50df0e1ec488)

https://github.com/modelcontextprotocol/inspector/commit/50df0e1ec488f3983740b4d28d2a968f12eb8979

Vendor Advisories for CVE-2025-49596(1)

These vendors published their own advisory mentioning this CVE — often with vendor-specific remediation steps + affected product lists not in NVD.

Patch Availability(1)

Vendor / EcosystemFix (by version range) / PatchReleasedSource
npm@modelcontextprotocol/inspector @ 0.14.1 (fixes < 0.14.1)—ghsa

Patches are aggregated from vendor advisories (Red Hat, Microsoft, Cisco, GitHub) and package ecosystems (OSV, GHSA). Multiple rows for the same upstream release have been deduplicated.

Affected Packages

(1 across 1 ecosystem)
npm(1)
PackageVulnerable rangeFix by version rangeDependents
@modelcontextprotocol/inspector—
  • every version up to 0.14.1: fixed in 0.14.1
—

Weakness Classification(1)

MITRE Common Weakness Enumeration — the root-cause categories this CVE belongs to.

Data Freshness Timeline

(refreshed 14× in last 7d / 41× in last 30d)

Each row is a time one of our pipelines fetched, updated or re-scored this CVE. For example, "NVD update" means NVD published or revised its analysis for this CVE; "MITRE cvelistV5" means we ingested or refreshed its CVE.org record (CNA or CISA ADP). An arrow marks a change the record states ("CVSS → 9.1"); EPSS and GHSA rows show the values recorded at that time, not what changed (EPSS values are rounded; hover one for the exact figures). "EchelonGraph re-scored" is our own recompute of this CVE's score, not an update from a source, and is not counted in the refreshes above. Most recent first.

Showing the most recent 100 of 262 rows on record for this CVE, as 96 entries (4 repeats merged).

A repeat, a row identical to one the same pipeline wrote less than 10 seconds earlier, is not a separate refresh and is not counted. 4 repeat rows among the latest 100 are merged into the row they repeat. The 162 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-11-13 02:35 UTCEchelonGraph re-scored
  2. 2026-11-13 02:35 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  3. 2026-11-12 16:32 UTCEPSS rescoreEPSS 40% · 98th percentile
  4. 2026-11-12 01:35 UTCEchelonGraph re-scored
  5. 2026-11-12 01:35 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  6. 2026-11-11 16:36 UTCEPSS rescoreEPSS 40% · 98th percentile
  7. 2026-11-11 00:34 UTCEchelonGraph re-scored
  8. 2026-11-11 00:34 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  9. 2026-11-10 16:40 UTCEPSS rescoreEPSS 40% · 98th percentile
  10. 2026-11-09 23:34 UTCEchelonGraph re-scored
  11. 2026-11-09 23:34 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  12. 2026-11-09 16:33 UTCEPSS rescoreEPSS 40% · 98th percentile
  13. 2026-11-08 22:34 UTCEchelonGraph re-scored
  14. 2026-11-08 22:34 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  15. 2026-11-08 16:37 UTCEPSS rescoreEPSS 44% · 98th percentile
  16. 2026-11-07 21:34 UTCEchelonGraph re-scored
  17. 2026-11-07 21:34 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  18. 2026-11-07 16:36 UTCEPSS rescoreEPSS 44% · 98th percentile
  19. 2026-11-06 20:34 UTCEchelonGraph re-scored
  20. 2026-11-06 20:34 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  21. 2026-11-06 16:34 UTCEPSS rescoreEPSS 44% · 98th percentile
  22. 2026-11-05 19:34 UTCEchelonGraph re-scored
  23. 2026-11-05 19:34 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  24. 2026-11-05 16:35 UTCEPSS rescoreEPSS 44% · 98th percentile
  25. 2026-11-05 14:25 UTCOSV refresh
Show 71 more
  1. 2026-11-04 18:34 UTCEchelonGraph re-scored
  2. 2026-11-04 18:34 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  3. 2026-11-04 16:33 UTCEPSS rescoreEPSS 44% · 98th percentile
  4. 2026-11-03 17:33 UTCEchelonGraph re-scored
  5. 2026-11-03 17:33 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  6. 2026-11-03 16:44 UTCEPSS rescoreEPSS 44% · 98th percentile
  7. 2026-11-02 16:33 UTCEchelonGraph re-scored
  8. 2026-11-02 16:33 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  9. 2026-11-01 15:13 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  10. 2026-11-01 08:05 UTCGHSA enrichmentGHSA-7f8r-222p-6f5g · GitHub severity CRITICAL
  11. 2026-11-01 08:05 UTCEchelonGraph re-scored
  12. 2026-10-31 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  13. 2026-10-31 14:13 UTCEchelonGraph re-scored
  14. 2026-10-30 16:32 UTCEPSS rescoreEPSS 44% · 98th percentile
  15. 2026-10-30 13:13 UTCEchelonGraph re-scored
  16. 2026-10-29 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  17. 2026-10-29 12:12 UTCEchelonGraph re-scored
  18. 2026-10-28 16:30 UTCEPSS rescoreEPSS 44% · 98th percentile
  19. 2026-10-28 11:05 UTCEchelonGraph re-scored
  20. 2026-10-27 16:30 UTCEPSS rescoreEPSS 44% · 98th percentile
  21. 2026-10-27 09:17 UTCEchelonGraph re-scored
  22. 2026-10-26 07:45 UTCEchelonGraph re-scored
  23. 2026-10-25 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  24. 2026-10-25 16:21 UTCEchelonGraph re-scored
  25. 2026-10-25 06:46 UTCEchelonGraph re-scored
  26. 2026-10-24 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  27. 2026-10-24 05:46 UTCEchelonGraph re-scored
  28. 2026-10-23 16:30 UTCEPSS rescoreEPSS 44% · 98th percentile
  29. 2026-10-23 04:43 UTCEchelonGraph re-scored
  30. 2026-10-22 16:33 UTCEPSS rescoreEPSS 44% · 98th percentile
  31. 2026-10-22 03:41 UTCEchelonGraph re-scored
  32. 2026-10-21 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  33. 2026-10-21 02:41 UTCEchelonGraph re-scored
  34. 2026-10-20 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  35. 2026-10-20 01:41 UTCEchelonGraph re-scored
  36. 2026-10-19 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  37. 2026-10-19 00:40 UTCEchelonGraph re-scored
  38. 2026-10-18 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  39. 2026-10-18 05:29 UTCEchelonGraph re-scored
  40. 2026-10-17 23:37 UTCEchelonGraph re-scored
  41. 2026-10-17 16:33 UTCEPSS rescoreEPSS 44% · 98th percentile
  42. 2026-10-16 22:37 UTCEchelonGraph re-scored
  43. 2026-10-16 16:38 UTCEPSS rescoreEPSS 44% · 98th percentile
  44. 2026-10-15 19:16 UTCEchelonGraph re-scored
  45. 2026-10-15 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  46. 2026-10-14 16:31 UTCEPSS rescoreEPSS 44% · 98th percentile
  47. 2026-10-14 13:06 UTCEchelonGraph re-scored
  48. 2026-10-13 16:32 UTCEPSS rescoreEPSS 44% · 98th percentile
  49. 2026-10-12 17:00 UTCEchelonGraph re-scored
  50. 2026-10-12 16:33 UTCEPSS rescoreEPSS 44% · 98th percentile
  51. 2026-10-11 20:33 UTCEchelonGraph re-scored
  52. 2026-10-11 18:45 UTCEchelonGraph re-scored
  53. 2026-10-11 15:20 UTCEchelonGraph re-scored
  54. 2026-10-10 20:53 UTCOSV refresh
  55. 2026-10-10 19:59 UTCEPSS rescoreEPSS 44% · 98th percentile
  56. 2026-10-09 20:06 UTCEPSS rescoreEPSS 44% · 98th percentile
  57. 2026-10-08 17:10 UTCEPSS rescoreEPSS 44% · 98th percentile
  58. 2026-10-07 23:47 UTCEPSS rescoreEPSS 44% · 98th percentile
  59. 2026-10-06 15:17 UTCEPSS rescoreEPSS 44% · 98th percentile
  60. 2026-10-04 23:21 UTCEPSS rescoreEPSS 44% · 98th percentile
  61. 2026-10-03 14:24 UTCEPSS rescoreEPSS 44% · 98th percentile
  62. 2026-10-01 19:49 UTCEPSS rescoreEPSS 44% · 98th percentile
  63. 2026-09-30 15:02 UTCEPSS rescoreEPSS 44% · 98th percentile
  64. 2026-09-26 15:58 UTCEPSS rescoreEPSS 44% · 98th percentile
  65. 2026-09-26 00:25 UTCEPSS rescoreEPSS 44% · 98th percentile
  66. 2026-09-24 14:02 UTCEPSS rescoreEPSS 44% · 98th percentile
  67. 2026-09-23 13:47 UTCEPSS rescoreEPSS 44% · 98th percentile
  68. 2026-09-21 21:06 UTCEPSS rescoreEPSS 44% · 98th percentile
  69. 2026-09-21 08:19 UTCOSV refresh
  70. 2026-09-20 20:15 UTCEPSS rescoreEPSS 44% · 98th percentile
  71. 2026-09-18 19:27 UTCEPSS rescoreEPSS 44% · 98th percentile

Public detection templates

(1 reference)

A public Nuclei detection template is referenced for this CVE. A detection template checks whether a system is affected; it is not necessarily exploit code.

  • Nucleihttp/cves/2025/CVE-2025-49596.yaml
    Published Sep 15, 2025

    MCP Inspector < 0.14.0 UnauthenticatedRemote Code Execution

    Open source ↗

Frequently asked(5)

What is CVE-2025-49596?
CVE-2025-49596 is a critical-severity vulnerability; its CVE record was published on June 13, 2025. The MCP inspector is a developer tool for testing and debugging MCP servers. Versions of MCP Inspector below 0.14.1 are vulnerable to remote code execution due to lack of authentication between the Inspector client and proxy, allowing unauthenticated requests to launch MCP commands over stdio.…
When was the CVE record for CVE-2025-49596 published?
The CVE record for CVE-2025-49596 was published on June 13, 2025. That is the record's publication date; the vulnerability itself may have been made public earlier. EchelonGraph's copy of the record carries a last-modified date of April 15, 2026; the record at its source may have been updated since.
Is CVE-2025-49596 actively exploited?
CVE-2025-49596 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 40% probability of exploitation in the next 30 days (98th percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2025-49596?
CVE-2025-49596 has a CVSS base score of 9.4 (NVD).
How do I remediate CVE-2025-49596?
A fix for CVE-2025-49596 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2025-49596 are linked in the Vendor Advisories panel on this page.

Dependency Blast Radius

See which npm, PyPI, Go, and Maven packages are affected by CVE-2025-49596

Explore →

Is Your Infrastructure Affected by CVE-2025-49596?

EchelonGraph automatically scans your cloud infrastructure and maps CVE exposure using blast radius analysis.