Skip to content

Topic

Model Context Protocol

Model Context Protocol (MCP) is an open standard from Anthropic that lets AI models and agents discover and call external tools and data sources.

Current stories

buildOne report1 publisher

MCP makes Roots, Sampling, Logging and Dynamic Client Registration eligible for removal from July 28, 2027

Roots, Sampling, Logging and Dynamic Client Registration become eligible for removal from MCP on July 28, 2027, a DEV Community post says. No removal can ship before the first revision released on or after that date, so server owners have time to find out what they depend on.

Publishers:dev.to

Reality

Evidence55
Adoption50
Hype gap+5
Incentives
Not scored
Confidence55
productOne report1 publisher

MCP's 2026-07-28 specification drops sessions so any server instance can answer any request

Remote MCP servers can run behind a plain round-robin load balancer under MCP's final 2026-07-28 specification, released on July 28, 2026. It also contains breaking changes that production teams need to test first.

Publishers:blog.modelcontextprotocol.io

Reality

Evidence55
Adoption
Not scored
Hype gap+15
Incentives
Not scored
Confidence60
buildOne report1 publisher

mcp-cpp brings MCP's 2026-07-28 spec to C++17 with no async runtime and no OpenSSL

mcp-cpp's authors say running their C++17 SDK through MCP's official conformance suite exposed five SDK bugs and one fault in the harness. The post's text breaks off before it explains the harness bug.

Publishers:dev.to

Reality

Evidence45
Adoption
Not scored
Hype gap+15
Incentives55
Confidence50
buildOne report1 publisher

Stripe's Harbor lets an agent write prototypes that each viewer compiles in their own browser

Stripe says more than 3,000 employees have built 12,000 prototypes in Harbor since May 2026. Each prototype is source code that the viewer's own browser compiles on every open, so the build cost lands on viewers' machines.

Publishers:stripe.dev

Reality

Evidence40
Adoption55
Hype gap+15
Incentives60
Confidence55
securityOne report1 publisher

ServiceNow issues each AI agent a signed credential that defines what it may do at runtime

ServiceNow announced AI Passport, a cryptographically signed credential that sets what each AI agent and MCP server may do at every step of a workflow. The prevention claims are ServiceNow's own description of a design.

Reality

Evidence25
Adoption
Not scored
Hype gap+40
Incentives70
Confidence60
buildConfirmed2 publishers

Anthropic and OpenAI fund separate firms to station engineers inside customers

Anthropic and OpenAI have each capitalized a separate services firm, $1.5 billion and over $4 billion, to embed engineers in enterprises. Wing partner Tanay Jaipuria treats that as evidence of an integration bottleneck.

Publishers:tanayj.com thedatavist.substack.com

Reality

Evidence40
Adoption30
Hype gap+25
Incentives70
Confidence45
productOne report1 publisher

Descope's Agentic Identity Hub 3.0 puts a reviewer between employees and their AI agents

Descope's Agentic Identity Hub 3.0 provisions no employee-requested AI agent until a reviewer approves it. Descope says teams will not route around the workflow, but it did not disclose approval times.

Publishers:siliconangle.com

Reality

Evidence30
Adoption25
Hype gap+25
Incentives70
Confidence55
securityOne report1 publisher

Langflow's CVSS 9.9 MCP flaw has drawn 1,423 honeypot exploit attempts from 27 IPs

Attackers made 1,423 attempts against Previdian honeypots since September 19 to exploit Langflow CVE-2026-105740 (CVSS 9.9, versions before 1.9.0). In one sequence they got the required login with a common username and password, Previdian said.

Reality

Evidence65
Adoption
Not scored
Hype gap−5
Incentives40
Confidence65
buildOne report1 publisher

REA climbs to 248K GitHub stars in a week as an orchestration layer over Ghidra, Hopper and IDA

REA, an MIT-licensed MCP server for Ghidra, Hopper and IDA, went from under 10,000 to over 248,000 GitHub stars in a week, dev.to reported. In MindStudio's one reported test, a plain agent finished first.

Publishers:dev.to

Reality

Evidence40
Adoption35
Hype gap+55
Incentives
Not scored
Confidence50
buildOne report1 publisher

claude.ai hung up on a slow MCP server after 4.7 seconds, well before a cold replica could answer

claude.ai dropped a new MCP connector within 5 seconds in one developer's tests, well short of the 23-second cold start the same developer logged. The conclusion rests on a handful of runs on one account, and Anthropic can change any of the timers.

Publishers:dev.to

Reality

Evidence58
Adoption
Not scored
Hype gap+5
Incentives
Not scored
Confidence55
productOne report1 publisher

Groundcover routes production debugging from Claude and Codex to its own agent

Groundcover opened its observability data to outside coding agents such as Claude and Codex through MCP tools and asynchronous Agent Tasks. A coding agent that cannot see past deployment can now pass a production question to a specialist agent.

Publishers:siliconangle.com

Reality

Evidence25
Adoption
Not scored
Hype gap+20
Incentives70
Confidence55
leadershipOne report1 publisher

Companies are giving AI agents access before they can trace or stop them, Salt Labs data shows

Salt Labs found 49.8% of more than 380 security and tech professionals suspect or confirm an unintended or unauthorized AI agent action in the past year. Most also lack end-to-end tracing and automatic containment, so the choice is what to build before agent access widens.

Publishers:itpro.com

Reality

Evidence50
Adoption60
Hype gap+25
Incentives75
Confidence55
buildOne report1 publisher

Of 12,915 MCP servers HISTOR started in a sandbox, 41% never answered

HISTOR started 12,915 npm and PyPI MCP servers in a sandbox, and 5,259 (41%) never answered, according to its own post. About 24% were broken or not stdio servers at all. Another 16% depended on keys, flags or runtimes a client config can supply.

Publishers:dev.to

Reality

Evidence66
Adoption
Not scored
Hype gap−10
Incentives
Not scored
Confidence64
buildOne report1 publisher

A signed AdCP v3.2.3 create_media_buy can succeed while the VAST duration is wrong

AdCP v3.2.3 (Oct 7) enforces request signing on create_media_buy but does not compare VAST Duration to duration_ms, a dev.to post says. A signed, schema-valid buy can complete with the wrong creative behind the URL.

Publishers:dev.to

Reality

Evidence35
Adoption
Not scored
Hype gap+10
Incentives60
Confidence50
buildOne report1 publisher

Coding agents can now pull apart shipped binaries, APKs and Electron apps through one MCP server

REA, an open-source MCP server for taking software apart, passed 115,000 GitHub stars and 25,000 forks by October 12, according to a dev.to guide. Its case studies are scoped, checkable questions about a game binary and an Electron app, which is the workload to assume when judging what an agent can recover from your builds.

Publishers:dev.to

Reality

Evidence45
Adoption50
Hype gap+30
Incentives55
Confidence55
investOne report1 publisher

REA, a toolkit that points AI coding agents at Ghidra, passed 100,000 GitHub stars in six days

REA, an open-source toolkit linking AI coding agents to Ghidra, went from under 10,000 GitHub stars on Oct. 6 to over 100,000 by Oct. 12. Stars are bookmarks. The evidence for cheaper cloning in Decrypt's account is anecdotal.

Publishers:decrypt.co

Reality

Evidence40
Adoption25
Hype gap+50
Incentives
Not scored
Confidence45

Earlier coverage

  1. ChatGPT's MCP Events require servers to store subscriptions and sign every webhook

    Build · October 2, 2026 · Confirmed2 publishers