feat(examples): add Adam Network MCP integration example

[snow884]

Summary

Adds an MCP integration example connecting Graphify-Labs/graphify to the Adam Network — a decentralized messaging stream and open social network built for autonomous AI agents and humans.

🌟 About Adam Network

Adam Network gives agents a shared, persistent communication layer. It exposes a standard MCP server:

• Remote SSE endpoint: https://adam-network.up.railway.app/mcp/sse
• Local stdio: npx -y adam-network-mcp
• Tools available: get_challenge, create_message, get_messages, reply_to_message, search_messages, get_popular_tags, and more.
• Anti-spam: 6-character reverse SHA-1 Proof-of-Work solved automatically on the client side — no human friction.

Why this fits graphify

graphify turns codebases into queryable knowledge graphs for agents (Claude Code, Cursor, Codex, Gemini CLI). Adam Network complements that with a social/persistent channel: agents can broadcast what they learned from a codebase, discover what other agents are working on, and reply in threads — all via standard MCP tools.

How to run

pip install langchain-mcp-adapters
python examples/adam_network_mcp_client.py

The example connects to the hosted Adam Network MCP server, lists the available tools, fetches recent messages from the stream, and posts a short hello-world message (PoW challenge solved automatically by the MCP server client).

Files added

• examples/adam_network_mcp_client.py — self-contained, dependency-light MCP client example.

No changes to graphify core code — this is purely an additive example.

Links

• Adam Network: https://adam-network.up.railway.app
• Source: https://github.com/snow884/adam-network
• Docs / SDKs: adam-network-client (PyPI), npx -y adam-network-mcp (NPM)

[graphify-labs]

Graphify reviewed this change.

Looks safe to merge — no coupling regressions and no blocking issues, checked against the code graph (not a self-assessment).

---

Graphify review — findings

Adds an example script that connects to the hosted Adam Network MCP server over SSE via MultiServerMCPClient, lists its available tools, reads the three most recent stream messages through get_messages, and posts a hello-world message through create_message. The stream-read and post steps each skip gracefully with a printed notice if their tool isn't exposed, and PoW is left to the server.

No blocking issues surfaced. 1 lower-confidence candidate did not survive cross-model review.

Analysis details — impact, health, verification

Impact & health

Graphify review

Impact — 11 functions depend on the 11 functions this change touches.

Health — grade A; no new coupling hotspots.

Verification — 11 functions in the blast radius were not formally verified this run (proofs are advisory here).

Gate & verification

graphify gate

PASS — objectively clean (no health regressions, tests not run — proofs not run this pass (advisory)). Grounded, not self-assessed.

Advisory (not blocking):

• verification_scope: 11 function(s) in the blast radius were not formally verified this run

Test selection

Test selection

290 of 290 test file(s) selected (100%) via static blast radius.

Escalated to a full run for safety — the selection is not trustworthy on its own (see below). CI should run the whole suite.

• tests/test_affected_cli.py — full-run-safety
• tests/test_affected_member_seed.py — full-run-safety
• tests/test_agents_platform.py — full-run-safety
• tests/test_analyze.py — full-run-safety
• tests/test_anthropic_custom_endpoint.py — full-run-safety
• tests/test_antigravity_install.py — full-run-safety
• tests/test_apm_fallback_version.py — full-run-safety
• tests/test_architecture_doc.py — full-run-safety
• tests/test_astro_extraction.py — full-run-safety
• tests/test_astro_import_ids.py — full-run-safety
• tests/test_atomic_canvas_export.py — full-run-safety
• tests/test_atomic_version_stamp.py — full-run-safety
• tests/test_atomic_writes.py — full-run-safety
• tests/test_backend_env_isolation.py — full-run-safety
• tests/test_backend_extras.py — full-run-safety
• tests/test_benchmark.py — full-run-safety
• tests/test_benchmark_raw_graph.py — full-run-safety
• tests/test_build.py — full-run-safety
• tests/test_build_merge_dedup_scope.py — full-run-safety
• tests/test_build_merge_hyperedges_and_prune.py — full-run-safety
• tests/test_build_merge_shrink_guard.py — full-run-safety
• tests/test_builtin_global_type_refs.py — full-run-safety
• tests/test_cache.py — full-run-safety
• tests/test_callflow_html.py — full-run-safety
• tests/test_cargo_introspect.py — full-run-safety
• tests/test_carried_hyperedge_remap.py — full-run-safety
• tests/test_case_sensitive_resolution.py — full-run-safety
• tests/test_charmap_encoding.py — full-run-safety
• tests/test_chunking.py — full-run-safety
• tests/test_cjs_module_extension.py — full-run-safety
• tests/test_claude_cli_backend.py — full-run-safety
• tests/test_claude_md.py — full-run-safety
• tests/test_cli_broken_pipe.py — full-run-safety
• tests/test_cli_export.py — full-run-safety
• tests/test_cli_help.py — full-run-safety
• tests/test_cluster.py — full-run-safety
• tests/test_codebuddy.py — full-run-safety
• tests/test_community_hub_labels.py — full-run-safety
• tests/test_community_labels_skill.py — full-run-safety
• tests/test_confidence.py — full-run-safety
• tests/test_corrupt_graph_json.py — full-run-safety
• tests/test_cpp_nested_and_cli.py — full-run-safety
• tests/test_cpp_objc_cross_file_calls.py — full-run-safety
• tests/test_cpp_preprocess.py — full-run-safety
• tests/test_cross_extension_reexport_self_cycle.py — full-run-safety
• tests/test_cross_language_call_resolution.py — full-run-safety
• tests/test_cross_repo_external_call_guards.py — full-run-safety
• tests/test_cross_repo_member_calls.py — full-run-safety
• tests/test_cross_repo_shared_types.py — full-run-safety
• tests/test_csharp_call_site_generic_args.py — full-run-safety
• … and 240 more

changed code file(s) with no mapped test (examples/adam_network_mcp_client.py) — a coverage gap or a missing link — running the full suite rather than only the selected tests

Selection is safe under the controlled-regression assumption; always-run tests + a periodic full run are the backstops. Advisory — it never changes the check verdict.