CVE-2026-52870

HIGHPre-NVD 7.67.6
EchelonGraph scoreMEDIUM confidence

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

This high-severity CVE scores 7.6 under a secondary CVSS source (NVD's own analysis pending). EPSS exploit probability: 0.4% (31st percentile of EPSS-scored CVEs). No GitHub Security Advisory CVSS is on record for this CVE.

Triggered by: Headline CVSS from a secondary CVSS source
Sources: EPSS, a secondary CVSS source
7.6EG
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: 0.4%CVSS: 7.6Exploit: None knownExposed services: Not assessed

A fix is available — apply it.

The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP). From 1.23.0 until 1.27.2, default handlers installed by server.experimental.enable_tasks() for tasks/list, tasks/get, tasks/result, and tasks/cancel operate only on task identifiers without recording the session that created each task, allowing any connected client to enumerate, read results from, consume messages for, or cancel other clients' tasks. This issue is fixed in version 1.27.2.

CVSS v3
7.6
EG Score
7.6HIGHmedium confidence
EG Risk
34
EG Risk 34/100

EG Risk is EchelonGraph's 0–100 priority score: it fuses intrinsic severity with real-world exploitation and automatability so you can rank equal-severity CVEs and fix the most dangerous first. Higher = act sooner. Distinct from the 0–10 EG Score (severity).

How it’s computed (value × EchelonGraph’s weight)
Severity76% × 45%
The EG Score, 7.6 of 10.
Exploitation0.4% × 40%
FIRST EPSS: the 30-day exploitation probability when EchelonGraph scored this CVE.
Automatability0% × 15%
CISA's SSVC Automatable value: no (Vulnrichment).
SSVC (CISA's decision table, applied by EchelonGraph): Track at every mission impact level.
Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (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
0.4%
EPSS %ILE
31st
KEV
Not listed

SSVC (CISA's decision table, applied by EchelonGraph)Track at every mission impact level.

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

Exploitation none (CISA Vulnrichment) · Automatable no (CISA Vulnrichment) · Technical impact partial (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)60 days if the affected system is publicly exposed; Fix on system upgrade if it is not.

In CISA KEV no (CISA's KEV catalog) · Automatable no (CISA Vulnrichment) · Technical impact partial (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

July 15, 2026

Last Modified

July 17, 2026

Advisory Details (4)

Auto-updated Jul 15, 2026
Patch available. Sources: github, github_commit, github_pr, github_release.
GitHub advisoryMentions a patch (unverified)

Experimental task handlers allow any client to access and cancel other clients' tasks · Advisory · modelcontextprotocol/python-sdk · GitHub

https://github.com/modelcontextprotocol/python-sdk/security/advisories/GHSA-hvrp-rf83-w775
GitHub release Patch Available

v1.27.2

Patch available: modelcontextprotocol/python-sdk v1.27.2

https://github.com/modelcontextprotocol/python-sdk/releases/tag/v1.27.2
GitHub pull request Patch Available

[v1.x] Scope experimental tasks to the session that created them

Patch available: modelcontextprotocol/python-sdk v1.27.2 (PR #2720 merged 2026-05-29)

https://github.com/modelcontextprotocol/python-sdk/pull/2720
GitHub commit Patch Available

commit 62137874ff26 (modelcontextprotocol/python-sdk)

Patch available: modelcontextprotocol/python-sdk v1.27.2 (contains commit 62137874ff26)

https://github.com/modelcontextprotocol/python-sdk/commit/62137874ff26dd74d2fea80ff528a7fd9ca7a5e7

Vendor Advisories for CVE-2026-52870(1)

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

Affected Packages

(1 across 1 ecosystem)
PyPI(1)
PackageVulnerable rangeFix by version rangeDependents
mcp1.23.0 ... 1.27.1 (9 versions)
  • 1.23.0 up to 1.27.2: fixed in 1.27.2
—

Weakness Classification(1)

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

Data Freshness Timeline

(refreshed 11× in last 7d / 33× 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 it from the CNA feed. An arrow marks a change the record states ("CVSS v3 → 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). Most recent first.

Showing the most recent 100 of 125 refreshes on record for this CVE.

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. None are among the latest 100 rows. The 25 oldest rows on record are not shown and were not checked, so the counts can still include repeats.

  1. 2026-10-13 16:34 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  2. 2026-10-12 16:34 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  3. 2026-10-12 15:58 UTCEG score recompute
  4. 2026-10-11 19:41 UTCEG score recompute
  5. 2026-10-11 16:56 UTCEG score recompute
  6. 2026-10-11 14:19 UTCEG score recompute
  7. 2026-10-11 13:49 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  8. 2026-10-10 20:00 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  9. 2026-10-09 20:07 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  10. 2026-10-08 17:12 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  11. 2026-10-07 23:48 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  12. 2026-10-06 15:18 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  13. 2026-10-05 17:43 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  14. 2026-10-04 23:22 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  15. 2026-10-03 14:26 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  16. 2026-10-02 17:56 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  17. 2026-10-01 19:50 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  18. 2026-10-01 12:36 UTCEG score recompute
  19. 2026-09-30 15:03 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  20. 2026-09-29 15:22 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  21. 2026-09-28 13:51 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  22. 2026-09-28 08:41 UTCEG score recompute
  23. 2026-09-27 13:48 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  24. 2026-09-26 15:59 UTCEPSS rescoreEPSS 0.4% · 30th percentile
  25. 2026-09-26 00:27 UTCEPSS rescoreEPSS 0.4% · 30th percentile
Show 75 more
  1. 2026-09-24 08:47 UTCEG score recompute
  2. 2026-09-23 17:53 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  3. 2026-09-23 03:14 UTCEG score recompute
  4. 2026-09-20 20:16 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  5. 2026-09-18 19:28 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  6. 2026-09-18 04:43 UTCEG score recompute
  7. 2026-09-16 14:08 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  8. 2026-09-16 05:15 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  9. 2026-09-13 23:11 UTCEG score recompute
  10. 2026-09-13 16:47 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  11. 2026-09-13 07:12 UTCEG score recompute
  12. 2026-09-11 21:44 UTCEG score recompute
  13. 2026-09-11 14:53 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  14. 2026-09-10 09:35 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  15. 2026-09-08 22:01 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  16. 2026-09-08 00:42 UTCEG score recompute
  17. 2026-09-07 16:01 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  18. 2026-09-06 13:47 UTCEPSS rescoreEPSS 0.4% · 32nd percentile
  19. 2026-09-05 20:48 UTCEG score recompute
  20. 2026-09-04 05:06 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  21. 2026-09-02 14:12 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  22. 2026-09-01 13:54 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  23. 2026-09-01 04:40 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  24. 2026-08-31 03:49 UTCEG score recompute
  25. 2026-08-30 19:17 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  26. 2026-08-30 03:45 UTCEG score recompute
  27. 2026-08-30 01:22 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  28. 2026-08-28 21:41 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  29. 2026-08-28 01:51 UTCEG score recompute
  30. 2026-08-27 14:25 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  31. 2026-08-26 23:43 UTCEG score recompute
  32. 2026-08-26 14:46 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  33. 2026-08-25 21:06 UTCEG score recompute
  34. 2026-08-25 13:49 UTCEPSS rescoreEPSS 0.4% · 31st percentile
  35. 2026-08-24 21:43 UTCEG score recompute
  36. 2026-08-24 09:58 UTCEG score recompute
  37. 2026-08-22 11:09 UTCEG score recompute
  38. 2026-08-21 23:49 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  39. 2026-08-20 23:55 UTCEG score recompute
  40. 2026-08-20 22:55 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  41. 2026-08-20 00:13 UTCEG score recompute
  42. 2026-08-19 17:04 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  43. 2026-08-18 22:25 UTCEG score recompute
  44. 2026-08-18 13:48 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  45. 2026-08-17 23:04 UTCEG score recompute
  46. 2026-08-17 13:47 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  47. 2026-08-16 23:44 UTCEG score recompute
  48. 2026-08-16 14:56 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  49. 2026-08-16 12:05 UTCEG score recompute
  50. 2026-08-16 02:14 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  51. 2026-08-15 12:47 UTCEG score recompute
  52. 2026-08-15 01:30 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  53. 2026-08-14 01:41 UTCEG score recompute
  54. 2026-08-13 22:00 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  55. 2026-08-12 14:44 UTCEG score recompute
  56. 2026-08-12 13:51 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  57. 2026-08-11 15:25 UTCEG score recompute
  58. 2026-08-11 03:46 UTCEG score recompute
  59. 2026-08-11 00:00 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  60. 2026-08-09 16:11 UTCEG score recompute
  61. 2026-08-09 13:46 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  62. 2026-08-08 16:53 UTCEG score recompute
  63. 2026-08-08 16:37 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  64. 2026-08-07 17:34 UTCEG score recompute
  65. 2026-08-06 18:16 UTCEG score recompute
  66. 2026-08-06 13:47 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  67. 2026-08-06 06:36 UTCEG score recompute
  68. 2026-08-05 19:17 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  69. 2026-08-04 19:38 UTCEG score recompute
  70. 2026-08-04 15:10 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  71. 2026-08-04 10:39 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  72. 2026-08-02 08:40 UTCEG score recompute
  73. 2026-08-02 02:27 UTCEPSS rescoreEPSS 0.2% · 14th percentile
  74. 2026-08-01 09:21 UTCEG score recompute
  75. 2026-08-01 04:16 UTCEPSS rescoreEPSS 0.2% · 14th percentile

Related CVEs(same product + same CWE)

Frequently asked(5)

What is CVE-2026-52870?
CVE-2026-52870 is a high-severity vulnerability; its CVE record was published on July 15, 2026. The MCP Python SDK, called mcp on PyPI, is a Python implementation of the Model Context Protocol (MCP). From 1.23.0 until 1.27.2, default handlers installed by server.experimental.enable_tasks() for tasks/list, tasks/get, tasks/result, and tasks/cancel operate only on task identifiers without…
When was the CVE record for CVE-2026-52870 published?
The CVE record for CVE-2026-52870 was published on July 15, 2026. 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 July 17, 2026; the record at its source may have been updated since.
Is CVE-2026-52870 actively exploited?
CVE-2026-52870 is not currently on CISA's Known Exploited Vulnerabilities catalog. FIRST EPSS estimates a 0.4% probability of exploitation in the next 30 days (31st percentile of EPSS-scored CVEs).
What is the CVSS score of CVE-2026-52870?
CVE-2026-52870 has a CVSS base score of 7.6 (a secondary CVSS source that NVD displays; NVD's own analysis pending).
How do I remediate CVE-2026-52870?
A fix for CVE-2026-52870 is available: update to the fixed version the vendor names in its advisory. The vendor advisories EchelonGraph has for CVE-2026-52870 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-2026-52870

Explore →

Is Your Infrastructure Affected by CVE-2026-52870?

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

Book a Demo →Browse All CVEs