threatdeck
Live 13:15 UTC ·

State of the MCP Ecosystem, 2026 Q4

Every server in the official MCP registry, measured: advisories that affect the version it ships, unpinned installs, remote-only and source-less servers, abandoned repositories and possible typosquats. Generated from MCP Server Watch data, reproducible from the downloads below.

Registry servers
68,913
42,624 publishers
Remote-only
61.3%
42,256 servers, code not reviewable
No source repository
36.7%
25,311 servers
Shipped version has an advisory
10
8 critical/high, 4 unfixed
Malicious-package records
5
OSV, across 66 packages with advisories
Unpinned installs
50
0.1%
Archived or stale repos
470
290 archived, 180 no commit in 12 months
Possible typosquats
1
name similarity, not verified

Key findings

  1. 61.3% of the 68,913 servers in the official MCP registry are remote-only: they publish a hosted endpoint and no package, so there is no code to review or pin.
  2. 36.7% link no source repository. Of the 43,502 that do, 18,603 had a commit in the last 30 days and 290 are archived.
  3. 10 servers ship a package version with a published advisory (18 distinct advisories); 4 have at least one with no fixed version.
  4. OSV lists 5 malicious-package records against packages that registry servers ship (any version), among 215 advisories on 66 packages.
  5. Beyond the registry, MCP Server Watch tracks 1,378 more servers found on GitHub (658), npm (465), Docker Hub (212), PyPI (43); they are not in these tables.
  6. The 10 largest publishers account for 16.3% of registry entries.
  7. 25,285 servers have a current version published in 2026-11 so far (16,283 in 2026-10).

Advisories affecting the shipped version

Servers by worst advisory severity
Servers by worst advisory severity Critical: 1 (10.0%); High: 7 (70.0%); Medium: 1 (10.0%); Low: 1 (10.0%) Critical: 1 servers (10.0%) Critical 1 (10.0%) High: 7 servers (70.0%) High 7 (70.0%) Medium: 1 servers (10.0%) Medium 1 (10.0%) Low: 1 servers (10.0%) Low 1 (10.0%)

A server counts once, under its most severe advisory.

Show table
GroupServersShare
Critical110.0%
High770.0%
Medium110.0%
Low110.0%
Supply-chain hygiene signals
Supply-chain hygiene signals Remote endpoint only: 42,256 (61.3%); No source repository: 25,311 (36.7%); Repository facts unavailable: 8,595 (12.5%); Archived repository: 290 (0.4%); No commit in 12 months: 180 (0.3%); Unpinned install: 50 (0.1%) Remote endpoint only: 42,256 servers (61.3%) Remote endpoint only 42,256 (61.3%) No source repository: 25,311 servers (36.7%) No source repository 25,311 (36.7%) Repository facts unavailable: 8,595 servers (12.5%) Repository facts unavailable 8,595 (12.5%) Archived repository: 290 servers (0.4%) Archived repository 290 (0.4%) No commit in 12 months: 180 servers (0.3%) No commit in 12 months 180 (0.3%) Unpinned install: 50 servers (0.1%) Unpinned install 50 (0.1%)

Signals are facts, not a verdict. A server can carry several.

Show table
GroupServersShare
Remote endpoint only42,25661.3%
No source repository25,31136.7%
Repository facts unavailable8,59512.5%
Archived repository2900.4%
No commit in 12 months1800.3%
Unpinned install500.1%
Top advisories by affected registry servers (at most 3 per package)
AdvisoryPackageSeverityServersFixed in
GHSA-2m9m-6cr5-9x25mssql-mcp-core: SQL injection in mssql-mcp write tools via unparameterized table names and WHERE clauses npm:@connorbritain/mssql-mcp-reader High 3 0.5.0
GHSA-p34x-fmph-9fjxFlyto2 Core: Arbitrary file write via unguarded data.*/file.* modules (incomplete fix of CVE-2026-67429) pypi:flyto-core Critical 1 2.26.8
GHSA-jx74-cqjv-2c67Flyto2 Core: Unauthenticated flyto-verification /run: callback_url SSRF and internal runner-secret exfiltration pypi:flyto-core Critical 1 2.26.7
GHSA-2956-977x-2w3rFlyto2 Core: Arbitrary file write via image.download (and other file-writing modules) pypi:flyto-core Critical 1 2.26.7
GHSA-mx6p-3fg7-v6pjobsidian-sync-mcp: Missing Host/Origin validation lets a public website drive a victim's Obsidian vault via DNS rebinding (no-auth mode) npm:obsidian-sync-mcp High 1 0.5.7
GHSA-fq6x-j3g6-xx83@rog0x/mcp-docker-tools: executes arbitrary code via the handleImageList function npm:@rog0x/mcp-docker-tools High 1 no fix listed
GHSA-2vq3-mpmf-9xgr@justice8096/sagemath-mcp-server: executes arbitrary code via the escapeShellString and sanitizeCode functions npm:@justice8096/sagemath-mcp-server High 1 no fix listed
GHSA-jwc4-922r-f2rw@rog0x/mcp-git-tools executes arbitrary code via the resolveBaseBranch function npm:@rog0x/mcp-git-tools High 1 no fix listed
GHSA-3r68-x3xc-rxpgwireshark-mcp vulnerable to arbitrary file write via export_objects when WIRESHARK_MCP_ALLOWED_DIRS is not configured pypi:wireshark-mcp Medium 1 no fix listed
GHSA-x3cv-r3g3-fpg9Neo4j Labs MCP Servers: SSRF and Data Modification via read_only Mode Bypass Through CALL Procedures pypi:mcp-neo4j-cypher Low 1 0.6.0

How servers are distributed

Servers by package registry
Servers by package registry Remote only (no package): 42,256 (61.3%); npm: 17,860 (25.9%); PyPI: 5,423 (7.9%); OCI (Docker): 1,990 (2.9%); MCP bundle (mcpb): 1,861 (2.7%); No package or remote: 687 (1.0%); NuGet: 186 (0.3%); Cargo: 153 (0.2%) Remote only (no package): 42,256 servers (61.3%) Remote only (no package) 42,256 (61.3%) npm: 17,860 servers (25.9%) npm 17,860 (25.9%) PyPI: 5,423 servers (7.9%) PyPI 5,423 (7.9%) OCI (Docker): 1,990 servers (2.9%) OCI (Docker) 1,990 (2.9%) MCP bundle (mcpb): 1,861 servers (2.7%) MCP bundle (mcpb) 1,861 (2.7%) No package or remote: 687 servers (1.0%) No package or remote 687 (1.0%) NuGet: 186 servers (0.3%) NuGet 186 (0.3%) Cargo: 153 servers (0.2%) Cargo 153 (0.2%)

A server can ship packages to several registries.

Show table
GroupServersShare
Remote only (no package)42,25661.3%
npm17,86025.9%
PyPI5,4237.9%
OCI (Docker)1,9902.9%
MCP bundle (mcpb)1,8612.7%
No package or remote6871.0%
NuGet1860.3%
Cargo1530.2%
Remote endpoints by transport
Remote endpoints by transport Streamable HTTP: 46,411 (98.4%); SSE (legacy): 1,123 (2.4%) Streamable HTTP: 46,411 servers (98.4%) Streamable HTTP 46,411 (98.4%) SSE (legacy): 1,123 servers (2.4%) SSE (legacy) 1,123 (2.4%)
Show table
GroupServersShare
Streamable HTTP46,41198.4%
SSE (legacy)1,1232.4%

Popularity and maintenance

GitHub stars of the declared repository
GitHub stars of the declared repository No GitHub repository: 25,411 (36.9%); Repository facts unavailable: 8,595 (12.5%); 0 stars: 20,554 (29.8%); 1–9: 10,463 (15.2%); 10–99: 2,661 (3.9%); 100–999: 939 (1.4%); 1k–9.9k: 230 (0.3%); 10k or more: 60 (0.1%) No GitHub repository: 25,411 servers (36.9%) No GitHub repository 25,411 (36.9%) Repository facts unavailable: 8,595 servers (12.5%) Repository facts unavailable 8,595 (12.5%) 0 stars: 20,554 servers (29.8%) 0 stars 20,554 (29.8%) 1–9: 10,463 servers (15.2%) 1–9 10,463 (15.2%) 10–99: 2,661 servers (3.9%) 10–99 2,661 (3.9%) 100–999: 939 servers (1.4%) 100–999 939 (1.4%) 1k–9.9k: 230 servers (0.3%) 1k–9.9k 230 (0.3%) 10k or more: 60 servers (0.1%) 10k or more 60 (0.1%)
Show table
GroupServersShare
No GitHub repository25,41136.9%
Repository facts unavailable8,59512.5%
0 stars20,55429.8%
1–910,46315.2%
10–992,6613.9%
100–9999391.4%
1k–9.9k2300.3%
10k or more600.1%
Last commit to the declared repository
Last commit to the declared repository Commit in last 30 days: 18,603 (27.0%); 31–90 days: 10,542 (15.3%); 91–365 days: 5,582 (8.1%); More than a year (stale): 180 (0.3%); Repository facts unavailable: 8,595 (12.5%); No GitHub repository: 25,411 (36.9%) Commit in last 30 days: 18,603 servers (27.0%) Commit in last 30 days 18,603 (27.0%) 31–90 days: 10,542 servers (15.3%) 31–90 days 10,542 (15.3%) 91–365 days: 5,582 servers (8.1%) 91–365 days 5,582 (8.1%) More than a year (stale): 180 servers (0.3%) More than a year (stale) 180 (0.3%) Repository facts unavailable: 8,595 servers (12.5%) Repository facts unavailable 8,595 (12.5%) No GitHub repository: 25,411 servers (36.9%) No GitHub repository 25,411 (36.9%)
Show table
GroupServersShare
Commit in last 30 days18,60327.0%
31–90 days10,54215.3%
91–365 days5,5828.1%
More than a year (stale)1800.3%
Repository facts unavailable8,59512.5%
No GitHub repository25,41136.9%
Servers by month their current version was published (last 12 months)
Servers by month their current version was published (last 12 months) 25-12: 192; 26-01: 276; 26-02: 761; 26-03: 1,399; 26-04: 1,508; 26-05: 1,945; 26-06: 2,225; 26-07: 3,418; 26-08: 5,480; 26-09: 9,442; 26-10: 16,283; 26-11: 25,285 25-12: 192 servers 25-12 26-01: 276 servers 26-02: 761 servers 26-02 26-03: 1,399 servers 26-04: 1,508 servers 26-04 26-05: 1,945 servers 26-06: 2,225 servers 26-06 26-07: 3,418 servers 26-08: 5,480 servers 26-08 26-09: 9,442 servers 26-10: 16,283 servers 26-10 26-11: 25,285 servers 25,285

The current month is partial.

Show table
MonthServers
25-12192
26-01276
26-02761
26-031,399
26-041,508
26-051,945
26-062,225
26-073,418
26-085,480
26-099,442
26-1016,283
26-1125,285

Possible typosquats

1 found

Low-star npm/PyPI packages whose name is one character away from a popular registry package, or that take a popular scoped package's name without its scope. Name similarity is a lead for review, not evidence of intent: these may be forks, renames or unrelated projects. ThreatDeck has not confirmed any of them as malicious.

PackageResemblesDifferenceStars (package / popular)
npm:concord-mcp npm:@concord-ai/concord-mcp scope dropped 2 / 1,005

AI Incident Ledger lists the OSV malicious-package records for registry packages with their sources.

Advisory speed

Time from an advisory's publication to its listing on this board (checked every 6 h), and how far the vendor or GitHub advisory came before NVD. Listing speed counts only advisories published after we started watching (2026-11-10); older advisories were back-filled. Median time to listing so far: 24.6 h over 2 advisories (90th percentile 44.8 h). Vendor/GHSA advisories came a median 18.1 h earlier than NVD.

ToolTrackedMeasuredMedian listingBefore NVDIn NVDLead vs NVD
OpenClaw 101 1 4.5 h 1/1 1 n/a
GitHub Copilot 7 1 44.8 h 0/1 7 n/a
Claude Code 32 0 n/a n/a 31 18 h earlier
Cursor 26 0 n/a n/a 26 27.4 h earlier
Roo Code 16 0 n/a n/a 16 15.5 h earlier
Zed (AI agent) 12 0 n/a n/a 12 5.8 h earlier
OpenAI Codex CLI 4 0 n/a n/a 4 46.3 h earlier
Aider 3 0 n/a n/a 3 0.7 h later
Cline 3 0 n/a n/a 2 19.6 d earlier
Continue 1 0 n/a n/a 1 n/a
Gemini CLI 1 0 n/a n/a 1 60.8 d earlier
goose 1 0 n/a n/a 1 17.1 d earlier
OpenHands 1 0 n/a n/a 1 3.3 d earlier

Tracked = advisories listed on the board (newest 100 per tool). Lead vs NVD = median time by which the vendor or GitHub advisory came before NVD's publication. "In NVD" counts advisories whose CVE has an NVD publication date so far (looked up a few at a time). Advisories that come from NVD itself have no lead time.

Methodology

  • Population: every server listed in the official MCP registry at the time of the crawl (68,913 servers, latest version of each). Servers that MCP Server Watch found elsewhere (npm, PyPI, GitHub, Docker Hub) are not in the tables; they are counted separately.
  • Repository facts (stars, last commit, archived) come from the GitHub API for the repository each server declares; servers without a GitHub repository have none.
  • Advisories come from OSV (GitHub Security Advisories, PyPI, OSSF malicious packages) for each npm/PyPI/NuGet/Cargo package a server ships. A server counts as affected only when an advisory's range includes the version the registry entry ships.
  • Signals are factual: unpinned = a package in the registry entry has no version or a floating one ("latest", "*") (0.1%); remote-only = only a hosted endpoint, no package or source to review (61.3%); no source = the registry entry links no repository; stale = no commit in 12 months; archived = the repository is archived.
  • Possible typosquats: npm/PyPI packages with fewer than 50 stars whose name is one character away from a registry package with 1,000+ stars, or that take a popular scoped package's bare name without its scope. The distinctive part of the popular name (generic tokens such as "mcp" and "server" removed) must be at least 5 characters; digit edits, the same publisher and the same repository are excluded.
  • Months count servers by the publication date of the registry entry's current version (re-published servers move to the month of their latest release).
  • Publisher concentration uses the registry namespace (the part before "/"); publisher names are not listed.
  • The report is regenerated on every publish from the same dataset as MCP Server Watch; the quarter's edition is frozen when the quarter ends. The JSON and CSV downloads contain exactly the tables shown.

Limitations

  • The official registry is a subset of the MCP servers developers run; many servers live only on npm, PyPI, Docker Hub or GitHub.
  • OSV coverage is incomplete: no advisory does not mean no vulnerability, and remote-only servers cannot be checked at all.
  • Advisory matching uses the version in the registry entry; installs that pin an older or newer version differ.
  • Stars measure attention, not quality or safety. Repository facts can be up to a few days old.
  • Name similarity is a lead for review, not evidence of intent: listed packages may be forks, renames or unrelated projects. None has been confirmed as malicious by ThreatDeck.
  • Registry entries can be published in bulk by a few namespaces, which inflates totals for some categories.

Reproduce and cite

The JSON and CSV hold every table on this page (aggregates and advisory/package ids only; no publisher names). Per-server data is browsable in MCP Server Watch and through the API. Cite as: ThreatDeck, "State of the MCP Ecosystem, 2026 Q4", data as of 2026-11-22.

Editions

  • 2026 Q4 running · generated 2026-11-22

Following

Follow the vendors, products, AI tools, techniques and actors you care about. Matching stories, CVEs and exploited bugs are marked, a Following tab appears in the feed, and returning visits show what changed. Saved only in this browser.

Presets

Get updates

A personal RSS feed of new stories on everything you follow. Paste it into any feed reader, Slack or Teams RSS app.