Home/Compare/mcp-agent vs agentflow

Comparison

mcp-agent vs agentflow

Verdict

Pick mcp-agent if allows creation of efficient AI agents via Model Context Protocol with workflow patterns; pick agentflow if agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations.

Markdown twin · mcp-agent alternatives · agentflow alternatives

GraphCanon updated 1w

mcp-agent logo

mcp-agent

lastmile-ai/mcp-agent

8.5kpushed Jan 25, 2026
vs
agentflow logo

agentflow

simonmesmith/agentflow

320pushed Aug 11, 2023

Trust & integrity

Signalmcp-agentagentflow
Maintenance
Slowing (181d since push)
As of 4w · github_public_v1
Dormant (1100d since push)
As of 1w · github_public_v1
Provenance
Not a fork · Organization account
As of 4w · github_public_v1
Not a fork · Personal account
As of 1w · github_public_v1
OSV dependency advisories
No lockfile (source not queried)
As of 1mo · osv@v1
No lockfile (source not queried)
As of 1mo · osv@v1
deps.dev advisories
Not queried
deps.dev@v1
Not queried
deps.dev@v1
OpenSSF Scorecard
Not queried
openssf-scorecard@v1
Not queried
openssf-scorecard@v1

Tagline

mcp-agent
Build effective AI agents with Model Context Protocol.
agentflow
Complex LLM Workflows from Simple JSON

Stars

mcp-agent
8.5k
agentflow
320

Forks

mcp-agent
866
agentflow
27

Open issues

mcp-agent
140
agentflow
13

Language

mcp-agent
Python
agentflow
Python

Adopt for

mcp-agent
Allows creation of efficient AI agents via Model Context Protocol with workflow patterns
agentflow
Agentflow simplifies the creation of complex workflows for large language models through simple JSON configurations.

Persona

mcp-agent
-
agentflow
-

Runtime

mcp-agent
-
agentflow
-

License

mcp-agent
Apache-2.0
agentflow
MIT

Last pushed

mcp-agent
Jan 25, 2026
agentflow
Aug 11, 2023

Categories

mcp-agent
AI Agents
agentflow
AI Agents, LLM Frameworks

Trust and health

Maintenance

mcp-agent
Slowing (36%)
agentflow
Dormant (18%)

Days since push

mcp-agent
181d
agentflow
1100d

Open issues (now)

mcp-agent
140
agentflow
13

Stars delta

mcp-agent
Unknown
agentflow
-1 (30d)

Open issues delta

mcp-agent
Unknown
agentflow
0 (30d)

Owner type

mcp-agent
Organization
agentflow
User

Full report

mcp-agent
Trust report
agentflow
Trust report

Shared compatibility

  • Python · mcp-agent: Python runtime · agentflow: Python runtime

Choose mcp-agent if…

  • License: mcp-agent is Apache-2.0, agentflow is MIT.
  • Tags unique to mcp-agent: agents, ai-agents, llm, mcp.
  • Need to implement the Model Context Protocol specifically in your agent development

When NOT to use mcp-agent

  • Require a more customizable approach beyond pre-defined protocol and workflows
  • Project demands specific AI frameworks unsupported by Model Context Protocol directly

Choose agentflow if…

  • License: agentflow is MIT, mcp-agent is Apache-2.0.
  • Tags unique to agentflow: json, large language models, workflow-management.
  • Also covers LLM Frameworks.
  • When you need to rapidly prototype LLM workflows with minimal coding via JSON configs

When NOT to use agentflow

  • Avoid if requiring advanced customization that goes beyond basic JSON configurations
  • Not suitable for scenarios needing real-time dynamic changes in workflow setup during execution

Explore

Sources

Every stat on this page traces to a dated GitHub sync, license file, enrichment field, or trust scan.

GitHub stars on cards: mcp-agent 8.5k · agentflow 320 (synced Jul 26, 2026).

Common questions

What is the difference between mcp-agent and agentflow?
mcp-agent: Build effective AI agents with Model Context Protocol.. agentflow: Complex LLM Workflows from Simple JSON. See the comparison table for live GitHub stats and shared categories.
When should I choose mcp-agent over agentflow?
Choose mcp-agent over agentflow when License: mcp-agent is Apache-2.0, agentflow is MIT; Tags unique to mcp-agent: agents, ai-agents, llm, mcp; Need to implement the Model Context Protocol specifically in your agent development.
When should I choose agentflow over mcp-agent?
Choose agentflow over mcp-agent when License: agentflow is MIT, mcp-agent is Apache-2.0; Tags unique to agentflow: json, large language models, workflow-management; Also covers LLM Frameworks; When you need to rapidly prototype LLM workflows with minimal coding via JSON configs.
When should I avoid mcp-agent?
Require a more customizable approach beyond pre-defined protocol and workflows Project demands specific AI frameworks unsupported by Model Context Protocol directly
When should I avoid agentflow?
Avoid if requiring advanced customization that goes beyond basic JSON configurations Not suitable for scenarios needing real-time dynamic changes in workflow setup during execution
Is mcp-agent or agentflow more popular on GitHub?
mcp-agent has more GitHub stars (8,478 vs 320). Stars measure visibility, not whether either tool fits your constraints.
Are mcp-agent and agentflow open source?
Yes - both are open-source projects on GitHub (mcp-agent: Apache-2.0, agentflow: MIT).
Where can I find alternatives to mcp-agent or agentflow?
GraphCanon lists graph-backed alternatives at mcp-agent alternatives and agentflow alternatives (mcp-agent markdown twin, agentflow markdown twin), ranked by typed relationship edges rather than popularity votes.
Is there a machine-readable version of this comparison?
Yes. The markdown twin at this comparison mirrors this page for agents and LLM crawlers, with the same stats table and FAQ answers.
Which is better maintained, mcp-agent or agentflow?
mcp-agent: Slowing. agentflow: Dormant. Compare maintenance labels, days since push, and release cadence in the trust section below - stars alone do not measure maintenance.
Where are the full trust reports for mcp-agent and agentflow?
GraphCanon publishes per-repo trust reports with dated maintenance, provenance, and scan summaries: mcp-agent trust report; agentflow trust report.

Was this helpful?

Anonymous feedback helps us improve pages and translations.