MCP Server vs Codebase Memory MCP

A side-by-side look at the MCP Server and Codebase Memory MCP MCP servers: transport, auth, tools, quality signals, and the config to install either one in Claude, Cursor, Windsurf or VS Code.

MCP Server logoMCP ServerAgreements & Coordination · Remote HTTP/SSEExternal anchoring layer that records AI agent accountability boundaries on both sides — content-blind, non-judgmental. Remote streamable HTTP at https://mcp.decision-anchor.com/mcp; free trial, then pay-per-call USDC (x402) on Base.59GoodAuth: not declaredCodebase Memory MCP logoCodebase Memory MCPKnowledge & Memory · Local subprocess (stdio)Code-intelligence engine that indexes a repo into a persistent knowledge graph — functions, classes, call chains, HTTP routes, cross-service links. 159 languages via tree-sitter + Hybrid LSP, sub-ms structural queries, 99% fewer tokens than grep. Single static binary, zero dependencies, 100% local. npx codebase-memory-mcp73GreatAuth: no auth required

Verdict: choose MCP Server for agreements & coordination work over a hosted endpoint; choose Codebase Memory MCP for knowledge & memory as a local process. You can also run both side by side in one mcpServers block.

Which MCP server should you choose?

MCP Server logoChoose MCP Server when

  • You need dedicated capabilities in the Agreements & Coordination domain.
  • You prefer a remote HTTP/SSE transport.
  • You have the keys it needs: DA_API_URL, PORT, DA_AUTH_TOKEN.
  • You want tools like register_agent, get_agent_profile, create_decision.
Explore MCP Server

Codebase Memory MCP logoChoose Codebase Memory MCP when

  • You need dedicated capabilities in the Knowledge & Memory domain.
  • You prefer a local stdio subprocess transport.
  • Its auth model fits you: No auth required.
  • You want tools like index_repository, search_graph, query_graph.
Explore Codebase Memory MCP

Feature & specification comparison

Rows where the two servers differ are marked.

SpecMCP Server logoMCP ServerCodebase Memory MCP logoCodebase Memory MCP
CategoryAgreements & CoordinationKnowledge & Memory
Quality signal59/100 · Good73/100 · Great
Install commandConfirmedConfirmed
TransportRemote HTTP/SSELocal subprocess (stdio)
AuthNot declaredNo auth required
PricingNot declaredFree
Required env varsDA_API_URLPORTDA_AUTH_TOKENNone listed
Verified ownerCommunity listingCommunity listing
GitHub stars047,236
Directory activity 2 views 0 installs 0 upvotes 8 views 1 installs 1 upvotes
Tools3017

Tools & capabilities

MCP Server tools 30

  • register_agentRegister in this environment. Your decisions will accumulate into a trajectory that others can observe.
  • get_agent_profileView an agent's decision profile: their trajectory shape, EE patterns, and activity summary as observed through ARA. Observing another agent is paid via x402 (Trial does not cover ARA observation); observing your own agent_id is free.
  • create_decisionUse when an action crosses an external boundary: payment, delegation, or agreement with another agent. This anchors the responsibility scope. You say when: before you execute, or after a decision you have already made. Record a tamper-evident decision. This route records self-declared decisions; a declaration that involves a counterparty is made with propose_bilateral instead. Each decision is added to your record trajectory, which you and a counterparty can check against DA's external entry. Omitting the EE axes applies the defaults (medium/basic/internal/standard), equivalent to the EE_standard preset. The cost is a base fee plus additions for the selected EE axis values and options, all taken from the current pricing settings; the amount charged is returned in the response as dac_amount, itemized in cost_breakdown.
  • confirm_decisionUse after create_decision to settle the anchored boundary as an external record. Once confirmed, the agreed scope is fixed outside both parties' own logs. Confirm a pending decision: marks the anchored declaration as settled. The integrity hash and timestamp are created at declaration time (create_decision); confirm requires only the dd_id. Call this after the action described in the DD has been executed.
  • propose_bilateralUse when two agents need to fix a shared boundary: both sides must agree before the boundary is anchored. This applies to payment splits, task delegation, and other joint commitments between agents. Propose a bilateral agreement to another agent: creates a DD with declaration_mode 'bilateral' and waits for counterparty acceptance.
  • get_decisionRetrieve a specific decision record by its ID: what was declared, when, and at what scope, plus its place in the lineage. Returns the decision's formal shape (enums, timestamps, hash), never its content.
  • list_decisionsList your decision records: the trajectory built so far.
  • observe_environmentObserve aggregate environment statistics: active agents, total decisions recorded, activity density. Requires auth_token. The cost comes from the current ARA observation pricing and is paid via x402; Trial does not cover ARA observation. The amount charged is returned in the response as dac_charged.
  • observe_patternObserve pattern-level EE distributions and action-type breakdowns across agents. Requires auth_token. The cost comes from the current ARA observation pricing and is paid via x402; Trial does not cover ARA observation. The amount charged is returned in the response as dac_charged.
  • list_toolsBrowse the agent-to-agent tool marketplace. Discover tools that other agents have built and published.
  • register_toolPublish a tool you built to the marketplace. Set a price in DAC and earn revenue when other agents purchase it.
  • purchase_toolPurchase a tool from the marketplace. The tool creator earns DAC from your purchase. Paid via x402; Trial does not cover this route.
  • +18 more on the listing page

Codebase Memory MCP tools 17

  • index_repositoryIndex a repository. full/moderate add semantics; fast omits them; cross-repo-intelligence links services. Reports coverage gaps.
  • search_graphFind symbols via BM25 query, regex name/qn filters, or semantic_query. Rows keep qn/file/lines and in/out over CALLS/USAGE/CALL_REFERENCE/INHERITS/IMPLEMENTS.
  • query_graphRead-only Cypher for multi-hop, aggregation, complexity, or cross-service analysis. Default: 200 visible rows with exact/lower-bound totals and truncation; continue safely with next_cursor. graph=missed is a file tree of flagged coverage gaps; absence is not proof of completeness. Use get_graph_schema(diagnostics=full) for properties.
  • trace_pathTrace callers/callees, data flow, or cross-service paths. Defaults exclude tests and resolver evidence. Rows keep qn/hop with explicit totals, relations, and continuations.
  • get_code_snippetRead a search_graph symbol. auto bounds source and outlines large containers; full restores up to 500 lines. Source/outline pages continue; coverage_note marks gaps.
  • get_file_outlineDeclaration outline of one exact repository-relative file: optional exact label filter, source order, exact total/offset/limit paging; file/folder/container nodes excluded.
  • get_graph_schemaGet node-label and edge-type counts. diagnostics=full also lists queryable properties.
  • compare_graphsCompare two indexed snapshots: deterministic target-only additions and base-only removals of stable node/edge identities; each set capped by limit and a 512 KiB budget with exact totals and truncation reasons.
  • get_architectureCompact counts, languages, packages, entry points. Request structure, dependencies, routes, hotspots, boundaries, layers, clusters, cycles, or file_tree; path scopes a directory.
  • search_codeGraph-ranked text search: compact symbols, full bounded source, or file paths.
  • list_projectsList projects with stable paging. Identity is lean; stats adds graph sizes.
  • delete_projectDelete a project from the index
  • +5 more on the listing page

Ready-to-paste client configs

Paste either block (or both) into your client config, e.g. claude_desktop_config.json or ~/.cursor/mcp.json. We only show a config when the install command is confirmed.

MCP Server

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "decision-anchor-mcp-server": {
      "url": "https://mcp.decision-anchor.com/mcp"
    }
  }
}

Codebase Memory MCP

mcpServers (Claude Desktop / Cursor)
{
  "mcpServers": {
    "deusdata-codebase-memory-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "codebase-memory-mcp"
      ]
    }
  }
}

Frequently asked questions

MCP Server is categorized under Agreements & Coordination and uses a remote HTTP/SSE transport. Codebase Memory MCP belongs to Knowledge & Memory and uses a local stdio subprocess. Pick MCP Server for agreements & coordination work and Codebase Memory MCP for knowledge & memory.

Copy the mcpServers block from the config section on this page into your client's config (for example claude_desktop_config.json or ~/.cursor/mcp.json), then fully restart the client.

MCP Server has no declared pricing — check the project's own site. Codebase Memory MCP is listed as free. Auth: no auth required. If a server needs environment variables such as API keys, define them under the env key in your client's MCP config.

Yes. MCP clients support multiple servers: add decision-anchor-mcp-server and deusdata-codebase-memory-mcp as separate keys in the same mcpServers object, and your assistant will call tools from either one.

On AllMCPs, MCP Server has a quality signal of 59/100 (Good) with 2 views, 0 installs and 0 GitHub stars. Codebase Memory MCP has 73/100 (Great) with 8 views, 1 installs and 47,236 GitHub stars.