{"id":"proofofwork-agency-reporecall","name":"reporecall","homepage":null,"repo_url":"https://github.com/proofofwork-agency/reporecall","category":"devtools","subcategories":[],"tags":["ai-coding","code-search","code-navigation","mcp","rag","local-first","tree-sitter","call-graph","memory"],"what_it_does":"Reporecall is a local developer-tool and MCP server/daemon that indexes a codebase (AST parsing + hybrid keyword/vector search + call-graph expansion) and injects relevant code and persistent “memory” into Claude Code prompts via a pre-submit hook. It also provides MCP tools for searching code and storing/recalling project memories on disk.","use_cases":["Speeding up code understanding for AI assistants (find symbols, callers/callees, call flows)","Building code navigation context for Claude Code before it answers","Persisting project knowledge and coding conventions across sessions via local memory files","Answering architectural/inventory questions with hybrid search and term expansion","Reducing repeated “grep chains” during interactive development"],"not_for":["Handling non-code/runtime behavior debugging where dynamic tooling is required","Cloud-hosted multi-tenant deployments needing centralized auth/audit","Use cases requiring strict type-resolved call graphs beyond name-based resolution"],"best_when":"You use Claude Code with local development on a TypeScript/JS-or-multi-language repo and want faster, context-rich retrieval (including callers/callees) with persistent local memory.","avoid_when":"You need a hosted API service with network access controls, or you require guaranteed type-accurate call graph edges; also avoid when queries are too vague to anchor on indexed symbols/terms.","alternatives":["Local grep+ripgrep + LSP tooling (manual or via agent)","Sourcegraph/Codebase search platforms (hosted)","Other RAG/code-intelligence tools with cloud indexing","Continue/Cody-style retrieval extensions using vector search"],"af_score":54.5,"security_score":46.5,"reliability_score":37.5,"package_type":"mcp_server","discovery_source":["github"],"priority":"high","status":"evaluated","version_evaluated":null,"last_evaluated":"2026-03-30T15:35:35.285755+00:00","interface":{"has_rest_api":false,"has_graphql":false,"has_grpc":false,"has_mcp_server":true,"mcp_server_url":null,"has_sdk":false,"sdk_languages":[],"openapi_spec_url":null,"webhooks":false},"auth":{"methods":["bearer-token auth for local daemon hook (localhost)"],"oauth":false,"scopes":false,"notes":"Authentication is described for the local daemon endpoint used by the prompt hook (localhost-only). No cloud/user auth flows are described."},"pricing":{"model":null,"free_tier_exists":false,"free_tier_limits":null,"paid_tiers":[],"requires_credit_card":false,"estimated_workload_costs":null,"notes":"No pricing information provided; appears local/OSS tooling installed via npm."},"requirements":{"requires_signup":false,"requires_credit_card":false,"domain_verification":false,"data_residency":["Local filesystem only (.memory/), optional local vector DB via LanceDB"],"compliance":[],"min_contract":null},"agent_readiness":{"af_score":54.5,"security_score":46.5,"reliability_score":37.5,"mcp_server_quality":78.0,"documentation_accuracy":60.0,"error_message_quality":0.0,"error_message_notes":null,"auth_complexity":85.0,"rate_limit_clarity":10.0,"tls_enforcement":40.0,"auth_strength":55.0,"scope_granularity":30.0,"dependency_hygiene":45.0,"secret_handling":60.0,"security_notes":"Runs locally (localhost-only daemon) and uses a bearer token for the hook endpoint per README, which reduces exposure surface. However, explicit TLS requirements, token storage/handling, and fine-grained authorization/scopes are not documented. The tool also ingests code and may store persistent memory on disk; operators should ensure filesystem permissions are appropriate. Dependency list is moderate; no CVE status is provided.","uptime_documented":0.0,"version_stability":65.0,"breaking_changes_history":40.0,"error_recovery":45.0,"idempotency_support":"false","idempotency_notes":"Not specified. Indexing/search operations are likely repeatable, but idempotency guarantees are not stated.","pagination_style":"none","retry_guidance_documented":false,"known_agent_gotchas":["Name-based call-graph edges may produce false edges in languages where types/disambiguation matter.","Retrieval can be weak for vague queries that lack an anchor symbol/term.","Token-budgeted context assembly may omit low-scoring or demoted test files, affecting answers that rely on tests.","Index staleness should be mitigated via local file watching, but behavior depends on daemon/indexing configuration."]}}