MCPGram is an MCP gateway for AI agents. It brings native OAuth apps and external MCP servers into one workspace, with a shared tool catalog and workspace controls for clients such as Claude Code, Cursor and Codex. Developers can connect apps, discover tools and enable or disable sources per workspace. The CLI provides login, synchronization and agent onboarding through one Universal Layer.
Who it is for
Developers and teams building AI agents with Claude Code, Cursor, Codex and other clients.
Problem it solves
Connecting tools separately in each AI client leads to repeated setup, duplicated credentials and configurations that drift between agents.
The solution
MCPGram brings native OAuth apps and external MCP servers into a shared workspace. Tools are discovered in one catalog, controlled per workspace and exposed to AI clients through a Universal Layer.
What makes it unique
Native app connectors and third-party MCP servers share one governed catalog. Teams can enable or disable sources per workspace without configuring each AI client separately.
Features1 listed
Native apps and external MCP servers
Connect OAuth apps and remote MCP endpoints in one tool catalog.
Details
Platforms
Web
·CLI
Pricing
Freemium
Built for
Developers and teams building AI agents with Claude Code, Cursor, Codex and other clients.
In IndieTools' mobile lab test on November 22, 2026, the MCPGram website scored 67 out of 100 (needs improvement). Largest Contentful Paint took 15.99 s and Speed Index took 8.59 s, both rated poor. It placed #1243 overall in the finalized week 2026-W46.
Measured (UTC)
LCPLargest Contentful Paint
15.99 s
Poor
TBTTotal Blocking Time
32 ms
Good
CLSCumulative Layout Shift
0.000
Good
FCPFirst Contentful Paint
1.05 s
Good
Ranked #1243 overall in 2026-W46, best #797.
MCPGram lab metrics
Speed metrics for MCPGram, measured November 22, 2026
Metric
Result
Status
Trend
Mobile lab testMid-range phone on a throttled 4G connection, two runs averaged. Changes compare with the run on Nov 21.
Performance score
Needs improvementDown 13 points
67 / 100
Needs improvementDown 13 points
First Contentful PaintFCP
Good162 ms faster
1.05 s
Good162 ms faster
Largest Contentful PaintLCP
Poor7.27 s slower
15.99 s
Poor7.27 s slower
Speed IndexSI
Poor411 ms slower
8.59 s
Poor411 ms slower
Total Blocking TimeTBT
GoodAbout the same
32 ms
GoodAbout the same
Cumulative Layout ShiftCLS
GoodAbout the same
0.000
GoodAbout the same
Unthrottled observationsTimed on the test machine's own fast connection, so they read lower than the lab metrics above.
Page loadLoad
837 ms slower
2.62 s
837 ms slower
Server responseTTFB
About the same
84 ms
About the same
MCPGram performance history
61 comparable mobile lab runs since September 30, 2026. Choose a metric and a range, then move along the line to read each run.
MCPGram Speed ranking
Weekly Speed standing for MCPGram
Weekly standingLatest finalized week 2026-W46. Bests cover the last 52 finalized weeks.
Stored lab observations from controlled test runs, not real-user Core Web Vitals or a guarantee of search rankings. Weekly standings remain attached to their finalized edition.Method psi-mobile-two-sample-mean-v1, 2 samples per reading. Lab results can vary between runs.
Ahrefs' newer model. It gives more weight to links from sites with organic search traffic and rates a subdomain on its own links.
DR3:
The previous model, shown in the Ahrefs app until 1 December 2026.
Model difference:
DR4 minus DR3 for the same domain. The models calculate differently, so this is not growth or a drop; the “since” lines compare each model with itself.