This server provides read-only access to pinned Bharosa documentation, API references, and code examples; it cannot access accounts or execute API requests.
List, search, and read bundled documentation with pagination and source provenance.
Search and read API reference docs, including operation details, parameters, schemas, and linked examples; method filters only filter text.
Search and read source-pinned SDK, cURL, and guide examples by language or operation ID, with validation scope and offset pagination.
Inspect snapshot versions, source hashes, checkpoint dates, review metadata, and provenance in tool responses.
Rely on deterministic local search only; no credentials, network access, arbitrary filesystem paths, account actions, or code execution.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@bharosa-docs-mcp find the create contract API operation and show a TypeScript SDK example"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Bharosa helps coding assistants plan and build integrations using an integration skill and seven read-only documentation tools. It cannot access accounts, execute API requests, transfer assets, or run examples.
Version 0.3.7 targets public bharosa@0.10.0 and the matching reviewed developer documentation. The exact canonical checkpoint, source hashes and snapshot versions are returned by the tools. This GitHub full-plugin release is separate from npm server publication and public directory acceptance.
The hosted service is https://mcp.bharosa.finance/; /up is its health check and /mcp is retired. The service serves a pinned documentation snapshot. Check tool response provenance when comparing it with the website.
Related MCP server: @prosodyai/mcp-docs
Extract the full-plugin release archive and run from its root:
codex plugin marketplace add .
codex plugin add bharosa-docs@bharosaFor Claude Code, use a session-only full plugin:
claude --plugin-dir ./plugins/bharosa-docsOr install its local catalogue persistently:
claude plugin marketplace add .
claude plugin install bharosa-docs@bharosaStart a new session. Ask: “Use the Bharosa integration skill to plan an own-account portfolio dashboard. Retrieve the relevant guides and examples, state their versions, and propose synthetic tests. Do not use real credentials.” In Claude Code the explicit skill is /bharosa-docs:bharosa-integration.
These install the skill and MCP connection together. A bare MCP connection does not install the skill. Codex desktop UI installation and Claude web skill loading are not proven by CLI tests. Your AI host needs its own login and usage allowance; the public documentation MCP needs no Bharosa login or key. No public directory approval is required for the local catalogue route.
bharosa_docs_list, bharosa_docs_search, bharosa_docs_read
bharosa_api_search, bharosa_api_details
bharosa_examples_search, bharosa_examples_read
All responses carry snapshot/source provenance. Search is literal and deterministic. Use returned IDs and pagination; reads are capped at 8,000 UTF-16 code units, with a universal serialized result cap of 131,072 bytes. API method filters select reference text, never an action. The integration skill provides grounded planning; there is no autonomous planner or account-action tool.
Use Node.js 22.12 or later on a supported LTS line. Install the reviewed tarball in an isolated project, then run its CLI directly:
npm install --ignore-scripts /absolute/path/bharosa-docs-mcp-0.3.7.tgz
node node_modules/bharosa-docs-mcp/dist/cli.js --check
node node_modules/bharosa-docs-mcp/dist/cli.js --stdioNo credentials, remote fetch or arbitrary filesystem paths are accepted by tools. Keep stdout reserved for MCP protocol messages.
Source organization: src/ runtime; scripts/ pinned generators/build/package verification; tests/ synthetic protocol/security/example checks; assets/ generated public corpus; plugins/ host manifests and skill. Runtime dependencies are bundled for offline installation. The development lock pins the verified public SDK archive and registry integrity. Source development requires the pinned public dependencies; clean archive consumption is separately tested.
npm run build
npm test
npm run verify:package
BHAROSA_MARKETING_ROOT=/path/to/reviewed/staged/public/input npm run docs:check
BHAROSA_MARKETING_ROOT=/path/to/reviewed/staged/public/input npm run coding:checkGenerators accept only pinned public source files. Website modules retain marketing source paths; separately staged public SDK contracts retain their original sdk/test/ paths and hashes. No private first-party contracts or licensed UI assets are included. Changing a source requires a reviewed checkpoint, regeneration, tests and a new release; installed snapshots do not refresh themselves.
The analytics reference includes the reviewed production metadata correction. Synthetic checks are not proof of an authenticated production journey. Determine delegated onboarding availability from the coordinated deployment evidence; this local candidate does not establish live availability. Do not invent OAuth endpoints or grant credentials.
MIT, with dependency notices in THIRD-PARTY-NOTICES.txt. Report issues at https://github.com/bhafin/plugin/issues using synthetic examples only. Never post credentials, financial records or private logs. Public docs: https://developers.bharosa.finance/docs/documentation-assistant#hosted . Directory listings remain pending.
Read one canonical API operation: method, path, parameters, body/responses and available source examples. Follow schema document IDs for referenced definitions. No API execution or credentials.
Inputs: operationId (required). Returns: notice, operation, exampleIds, reviewedOn, +13 more
Search bundled API reference documents. Every result is documentation text, including references describing write endpoints. The optional method filter matches a documented HTTP verb; it does not send a request or select an action to execute. This tool only reads a local index and can never read or write an account.
Inputs: query (required), group, limit, method. Returns: total, notice, matches, reviewedOn, +12 more
List bundled public documentation. Offset is a document index; at most 20 results. No filesystem or network access from arguments.
Inputs: limit, offset. Returns: total, notice, documents, nextOffset, +10 more
Read bundled documentation by its allowlisted ID from bharosa_docs_list. Offset and maxChars count UTF-16 code units; at most 8000 per response. No path or URL input.
Inputs: id (required), offset, maxChars. Returns: notice, offset, content, document, +11 more
Search bundled IDs, titles and text using case-insensitive literal AND terms, ranked by exact ID/title and title matches with source-order ties. At most 120 query characters and 20 results; no regex or remote search.
Inputs: query (required), limit. Returns: total, notice, matches, reviewedOn, +9 more
Read a canonical example by allowlisted ID, its optional initialization context and source hash. UTF-16 offsets; at most 8000 code units. Returns text only; never executes code.
Inputs: id (required), offset, maxChars. Returns: code, setup, notice, offset, +15 more
Find source-pinned SDK, cURL and guide examples by literal query, language or operation ID. Reports precise synthetic/typecheck/syntax validation scope; no live integration claim.
Inputs: query (required), limit, language, operationId. Returns: total, notice, matches, reviewedOn, +12 more
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Scored across 7 tools
Each tool is explicitly scoped to one artifact type (API operations, source examples, general docs), and the read-only nature is repeatedly stated, which helps avoid confusion with execution tools. The only real overlap is between bharosa_api_search and bharosa_docs_search, since API reference content may also be covered by the general docs index; the descriptions hint at this but don't fully disambiguate which to pick first.
All tools share the bharosa_ prefix and a strict noun_verb pattern grouped by collection (docs_list/search/read, examples_search/read, api_search/details), so the set is highly predictable. The one deviation is bharosa_api_details standing in for the *_read slot, which is slightly inconsistent with examples_read and docs_read.
Seven tools is well-scoped for a bundled, read-only documentation server: three collections each get the minimal list/search/read or search/read pair they need. Nothing looks redundant or padded, and no collection is left without a retrieval path.
The read-only documentation lifecycle (list, search, read) is covered for docs and examples, with search/details for API operations and source examples, so agents rarely hit a dead end. The main gap is the absence of an api_list or operation-enumeration tool, forcing agents to discover operations only via search, and there is no way to browse examples for an operation without a literal query.
Read-only MCP tools for AI agent discovery, structured resources, and NIULAI information.
Pay-per-use tool marketplace for AI agents. Search, price-check, and call APIs via MCP.
Read-only search of 2,189 AI agent tools (MCP servers, x402 APIs) with daily automated trust scores.
Team docs served to AI agents over MCP - search, Markdown reads, version pinning, read audit.
