# io.github.khaoss85/agent-crm Read-only docs for the Accordo CRM framework: what it proves, and where it stops. - **Type:** MCP server - **Trust:** 60/100 (B), scored on the content rubric - **Verification:** community-indexed — nobody has claimed this listing - **Version:** 0.1.0 - **Author:** io.github.khaoss85 - **License:** Unknown - **Endpoints:** streamable-http https://accordo.dev/api/mcp - **Source:** https://github.com/khaoss85/agent-crm - **Endpoint health:** reachable (last checked 2026-08-30T00:17:55.255Z, 1 sample) — uptime is not a security property and is not part of the trust score - **Compatible clients:** claude-code, cursor, copilot, chatgpt, gemini (basis: transport) ## Trust 60/100 (B), scored on the content rubric - Publisher verified: no - Install scripts: nothing suspicious found - Prompt-injection scan: clean - Obfuscation scan: clean - Evidence age: 0 days ## Security scan - **Status:** clean - **Scanned:** 2026-09-05T13:32:34.741Z - **Version scanned:** HEAD - **CVEs:** no coverage — this entry has no package coordinates to query OSV against, so "no known CVEs" is NOT asserted for it. ## Tools 32 declared. Statically extracted from the shipped source — a floor on the surface, not a census. - `company` — An organization with which the business has a relationship. - `contact` — A person associated with a company. - `opportunity` — A new-business, renewal or upsell commercial process. - `approval` — A human decision required by an explicit commercial policy. - `documentation-index` — Every document this server serves, what it is, and what is deliberately excluded. - `claims-ledger` — Every public capability claim bound to the tests that prove it, each paired with the limitation - `jobs-index` - `search_docs` — Keyword search across this framework's documentation set (README, AGENTS, ARCHITECTURE, PRODUCT, - `get_capability` — Resolve a capability from the claims ledger by id (C-nn), by standing-limitation id (L-nn), or by topic. - `check_job` — Answer "can this framework do X?" against the CRM jobs-to-be-done index. Returns the matching jobs with - `architecture` — The repository architecture and extension rules. - `jobs-to-be-done` — Medusa-style use cases translated to CRM. - `build-crm-feature` — Turn a business request into a safe module/workflow implementation plan. - `business_request` — The commercial outcome to implement. - `debug-crm-run` — Inspect a workflow trace and produce a minimal regression-safe fix. - `run_id` — Workflow run UUID. - `crm-schema` — Current CRM entities, fields, money and state conventions. - `crm-modules` — Module metadata available in the running application. - `crm-workflows` — Deterministic processes and their named steps. - `crm_project_context` — Inspect modules, workflows, providers, schema and architectural rules before changing the project. - `crm_list_opportunities` — List new-business, renewal or upsell opportunities with optional stage, type and company filters. - `crm_create_opportunity` — Create an opportunity through the Opportunity module service, preserving validation and audit. - `crm_request_stage_change` — Run the controlled stage-change workflow. High-value renewals moving to Proposal require human approval. - `crm_list_approvals` — List pending, approved or rejected human approval requests. - `crm_decide_approval` — Record an explicit human approval or rejection and apply the resulting opportunity stage. - `crm_get_trace` — Read a workflow run with step-level inputs, outputs, status and errors. - `crm_scaffold_module` — Plan or create a module service, metadata and test skeleton. Defaults to dry-run; apply must be explicitly true. - `crm_doctor` — Inspect database, modules, workflows, providers and entity counts. - `decide-opportunity-approval` — Records a human approval decision and applies the resulting opportunity stage. - `request-opportunity-stage-change` — Moves an opportunity while enforcing explicit approval policy. - `lead` — Inbound leads. - `widget` — an evolvable record ## Install **Verdict: review** — Installable, but 2 things to check first: No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it. **Cautions** (coverage gaps and advisories — never blocking) - No CVE coverage: this entry has no npm/PyPI coordinates to query OSV against, so "no known vulnerabilities" is not a claim that can be made about it. - No publisher has proved control of this listing; it is indexed, not vouched for. **Config** (claude-code): ```json "{\n \"mcpServers\": {\n \"agent-crm\": {\n \"type\": \"http\",\n \"url\": \"https://accordo.dev/api/mcp\"\n }\n }\n}" ``` ## Blast radius Contained to moderate — no credential declaration found, from the publisher, the upstream registry, or the README. Known so far: runs on someone else's infrastructure; read-only tool surface. - Floor 9, ceiling 27 (tier: unknown) - `unknown` means the floor and ceiling land in different bands — not measured enough to name one. It does not mean low. - This is impact, not likelihood. A high radius is not a defect: a filesystem server is supposed to write files. It is never part of the trust score. ## Machine-readable views of this entry - Signed JSON: https://forgeregistry.com/api/v1/packages/io.github.khaoss85%2Fagent-crm - Install plan: https://forgeregistry.com/api/v1/packages/io.github.khaoss85%2Fagent-crm/install-plan - Alternatives: https://forgeregistry.com/api/v1/alternatives/io.github.khaoss85%2Fagent-crm - HTML page: https://forgeregistry.com/registry/io.github.khaoss85%2Fagent-crm - MCP: POST https://forgeregistry.com/api/mcp → `forge_get_package` / `forge_install_plan` ## About this document Generated by Forge (https://forgeregistry.com) — a compact rendering of the same record served, signed, at the JSON URL above. Trust and scan facts are the registry's own measurements; anything Forge did not measure is named as unmeasured rather than omitted.