Click on "Install 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., "@advocatehub-mcp list all active members in the 'Gold' group"
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.
A Model Context Protocol server for
Influitive AdvocateHub, built entirely on the
public Influitive REST API (api.influitive.com / api.influitives.com in
staging). This is Phase 1: no hub source changes, no internal endpoints —
everything here is something any AdvocateHub customer could build against
their own API token.
55 org-token tools (members, groups, challenges, events, rewards, approvals,
referrals, references, webhooks, messages, integrations, and more) plus
25 individual-user SSO / JWT self-service tools (sso_login, whoami,
sso_logout, and 22 my_* tools covering profile, groups, challenges, rewards,
activity, notifications, badges/achievements, and social auth). Org-token writes
are confirm-gated and audit-logged; SSO tools sign a human into their own hub
account via a real browser and call the hub as them, separate from the org-wide
API token.
Tool surface (HTTP-first): streamable HTTP defaults to the gateway surface
(~20 category tools). Set header X-Advocatehub-Tool-Surface: granular for the full
~83 granular catalog (e.g. Cursor). Claude Desktop is auto-detected from MCP
initialize clientInfo. Stdio defaults to granular unless
ADVOCATEHUB_TOOL_SURFACE=gateway. See docs/tool-reference.md
for gateway actions and docs/setup-claude.md for setup.
Related MCP server: hubspot-mcp
P1a (stdio, for Claude Desktop/Code): done. See docs/setup-claude.md.
P1b (streamable HTTP, for ChatGPT / remote clients): done, needs a staging smoke pass. See docs/setup-chatgpt.md.
Individual-user SSO/JWT self-service (sso_login/whoami/sso_logout + 22 my_* tools,
see src/tools/myAccount.ts and src/tools/sso.ts): done for stdio only. See
docs/setup-sso.md. Not yet available on the streamable
HTTP transport.
Target environment so far: staging (https://api.influitives.com).
Production support is a config change (X-Influitive-Base-Url header or
INFLUITIVE_BASE_URL env var to https://api.influitive.com) — re-run the
staging smoke checklist against production before trusting it there.
File-grounded improvement plans by credential model:
Org token + org id (integration / admin bot): docs/optimization-plan-org-token.md
Individual JWT / SSO (self-service, signed-in human): docs/optimization-plan-jwt-sso.md
Both credentials (hybrid stdio deployments): docs/optimization-plan-hybrid.md
See also JWT_INDIVIDUAL_USER_AUTH_CAPABILITY_MATRIX.md for what each credential can and cannot do today.
npm install
npm run build
npm run start:http # listens on PORT (default 8787), no credentials neededPoint your MCP client at http://localhost:8787/mcp with per-connection headers:
{
"mcpServers": {
"advocatehub": {
"type": "http",
"url": "http://localhost:8787/mcp",
"headers": {
"Authorization": "Bearer <INFLUITIVE_API_TOKEN>",
"X-Influitive-Org-Id": "<ORG_ID>",
"X-Influitive-Base-Url": "https://api.influitives.com"
}
}
}
}See docs/setup-claude.md and docs/setup-chatgpt.md
for Claude Desktop, Claude Code (claude mcp add --transport http), and ChatGPT setup.
See docs/usage-guide.md for credential modes and which tools each auth type exposes.
npm install
npm run build
npm run start # or point your client's config at dist/src/index.jsSupply credentials via client env vars (INFLUITIVE_API_TOKEN, INFLUITIVE_ORG_ID)
or call the configure_tenant tool at session start. No .env file or setup
wizard required.
Use stdio transport and configure both credentials:
# Org-wide integration bot (required for admin tools)
INFLUITIVE_BASE_URL=https://api.influitives.com
INFLUITIVE_API_TOKEN=<from hub Admin -> Integrations -> Influitive API>
INFLUITIVE_ORG_ID=<numeric org id>
# Individual-user SSO (required for sso_login / whoami / my_* tools)
INFLUITIVE_HUB_URL=https://yourhub.influitives.comOr pass hub_url to configure_tenant alongside api_token and org_id.
After configuration, run sso_login once interactively to seed the browser profile. SSO tools do not work on streamable HTTP — see docs/setup-sso.md and docs/optimization-plan-hybrid.md.
npm run dev # tsx watch, stdio
npm run dev:http # tsx watch, streamable HTTP
npm test # unit tests (mocked fetch, no network)
npm run test:integration # opt-in, hits real staging — see .env.example
npm run lint
npm run typechecksrc/
index.ts stdio entrypoint (P1a)
http.ts streamable HTTP entrypoint (P1b)
server.ts builds the McpServer and registers all tools
config/ tenant session, HTTP header resolution, env bootstrap, SSO session cache
client/ InfluitiveClient: auth headers, retries, cursor pagination, rate limiting
auth/ HubSsoClient: Playwright-driven individual-user SSO login (see docs/setup-sso.md)
errors/ typed error classes + HTTP status -> error mapping
registry/ local per-tenant index of challenges this server has created
audit/ append-only JSONL write audit log (monthly rotation)
tools/ ~55 org-token tools + configure_tenant + 25 SSO/JWT self-service tools
test/
unit/ fast tests, fetch mocked, no network
integration/ opt-in, mutates a real (disposable) staging tenant
docs/ setup guides, usage guide, tool referencePlug-and-play credentials: the server starts unconfigured. HTTP clients
pass Authorization, X-Influitive-Org-Id, and optionally
X-Influitive-Base-Url per connection. Stdio clients use env vars or
configure_tenant at runtime.
Write safety: every write tool takes a confirm flag. confirm:false
(or omitted) only previews — it never calls the API. confirm:true executes
and always appends exactly one entry to the per-tenant audit log
(~/.advocatehub-mcp/audit/<orgId>-YYYY-MM.jsonl, with legacy
<orgId>.jsonl still read), whether it succeeded or failed.
See src/tools/shared/confirmGate.ts.
No raw exceptions cross the MCP boundary. Every tool handler is wrapped
so typed errors (AuthError, NotFoundError, ...) come back as
{ isError: true } text, never an unhandled throw. See
src/tools/shared/formatters.ts.
The public API has no "list challenges" endpoint. ChallengeRegistry
(src/registry/challengeRegistry.ts) is a local, best-effort index of
challenges this server created — it does not know about challenges
created any other way, and is lost if ~/.advocatehub-mcp is wiped.
contacts_api_search is a per-tenant Labs flag. If it's off, /contacts
silently ignores filters instead of erroring. search_members refuses
filtered queries once it knows the flag is off (config.contactsSearchEnabled === false), and self-heals that cache the first time it sees evidence
either way. See src/tools/members.ts.
Locking a member is seat reclaim, per current product policy: it blocks
login and excludes the member from advocate counts, targeting, and the
billable seat count. deactivate_member/reactivate_member describe this
explicitly in their tool descriptions so an LLM doesn't undersell what the
action does.
Search executed write audit entries for this tenant. Filter by tool name, actor type (org_token or sso), and optional ISO date range. Reads ~/.advocatehub-mcp/audit/-YYYY-MM.jsonl (and legacy .jsonl).
| Name | Required | Description | Default |
|---|---|---|---|
| tool | No | Filter by write tool name, e.g. "log_event". | |
| limit | No | Max matching entries to return (newest first, max 500). | |
| end_at | No | Inclusive upper bound (ISO 8601). | |
| start_at | No | Inclusive lower bound (ISO 8601), e.g. "2026-01-01T00:00:00.000Z". | |
| actor_type | No | Filter by credential type that performed the write. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false. The description adds valuable behavioral context by disclosing it reads local files at ~/.advocatehub-mcp/audit/<orgId>-YYYY-MM.jsonl and legacy <orgId>.jsonl, which informs the agent about filesystem access and legacy support. No contradiction with annotations.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences: the first states purpose and filters, the second states storage location. There is no fluff, and the most important information is front-loaded.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
The description is complete enough for a read-only search tool with no output schema. It covers the resource, supported filters, and file location. It does not explicitly mention return format or ordering, but the schema's limit parameter and annotations provide some context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100% with detailed descriptions for all parameters. The description merely summarizes the filter fields ('tool name, actor type, ISO date range') without adding new information beyond the schema, so it does not compensate beyond the schema coverage baseline.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Search executed write audit entries for this tenant' with a specific verb and resource, and lists filter dimensions (tool name, actor type, ISO date range). It does not explicitly differentiate from the sibling audit_tail, but the word 'search' implies historical querying as opposed to tailing.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies usage for querying historical write audit entries with optional filters, giving clear context. However, it does not explicitly state when not to use it or mention alternatives like audit_tail for live tailing, so it lacks explicit exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Return the last N executed write audit entries for this tenant from ~/.advocatehub-mcp/audit/-YYYY-MM.jsonl (and legacy .jsonl if present). Only confirm:true writes are logged; previews are excluded.
| Name | Required | Description | Default |
|---|---|---|---|
| limit | No | Number of most recent audit entries to return (max 500). |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, so the bar is lower. The description adds meaningful behavior beyond annotations: it specifies the exact file location, the fact that only confirm:true writes are logged, and that previews are excluded. This gives the agent useful expectation about data availability.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences and front-loaded with the main purpose. Every piece of information (file path, filtering rule) is relevant and efficiently communicated without redundancy.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
There is no output schema, so the description could have explained the structure of each audit entry. It does specify the source file and filtering, but not the fields of the returned entries. Overall, this is reasonably complete for a simple tail tool with good annotations, but a short note on output format would have made it complete.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The only parameter 'limit' is fully described in the input schema with a default, range, and description, so schema coverage is 100%. The tool description itself does not add extra parameter semantics, but with full schema coverage, the baseline of 3 is appropriate.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states a specific action (Return), a specific resource (write audit entries), and the scope (last N for this tenant, from a specific file path). It also distinguishes from the sibling audit_search by implying a tail operation rather than a search.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description implies the tool is used to retrieve recent confirmed write audit entries, but it does not explicitly mention when to choose this over audit_search or other siblings. The note about 'confirm:true' and previews exclusion provides some context but no direct usage alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Supplies org-wide API credentials (api_token + org_id) and/or hub_url for SSO. Required before other tools when the server started unconfigured. Org-token tools need api_token + org_id; SSO-only sessions need only hub_url (org id is derived from the JWT after sso_login).
| Name | Required | Description | Default |
|---|---|---|---|
| org_id | No | Numeric organization id (X_ORG_ID). Required with api_token. | |
| hub_url | No | Hub web app origin for SSO tools (e.g. https://yourhub.influitives.com). | |
| base_url | No | REST API origin (default: https://api.influitives.com). | |
| validate | No | When true (default), validates org credentials via GET /api/members/me when api_token is supplied. | |
| api_token | No | Narci API token from hub Admin → Integrations → Influitive API. Optional for SSO-only. |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=false and destructiveHint=false. The description adds behavioral context by explaining the precondition ('Required before other tools') and the validation behavior via the 'validate' parameter. It does not disclose all side effects (e.g., whether credentials are persisted), but it goes beyond what annotations alone provide.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Three sentences, front-loaded with the core purpose, then prerequisites, then parameter-mode rules. No fluff; every sentence serves a distinct purpose.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the tool's moderate complexity (5 params, no output schema), the description covers the main modes, a prerequisite, and validation behavior. It does not describe return values, but that is less critical for a setup tool. The schema already documents all parameters, so the description is appropriately complementary.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema coverage is 100%, so baseline is 3. The description elevates this by explaining the semantic relationships between parameters: 'Org-token tools need api_token + org_id; SSO-only sessions need only hub_url (org id is derived from the JWT after sso_login).' This is meaningful guidance not present in the schema.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the tool's verb and resource: 'Supplies org-wide API credentials (api_token + org_id) and/or hub_url for SSO.' It also distinguishes itself from siblings by framing itself as a prerequisite setup tool, distinct from listing, auditing, and identity-context tools.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description explicitly says when to use the tool: 'Required before other tools when the server started unconfigured.' It also provides mode-specific guidance (org-token vs. SSO-only). However, it does not explicitly state when NOT to use it or mention alternative tools, falling short of the '5' bar for explicit exclusions/alternatives.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Reports which credentials are active in this MCP session: org-wide API token (when configured) and individual-user SSO (when hub_url is set or after sso_login). Call before choosing org-token admin tools vs my_* / SSO self-service tools.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, but the description adds valuable context about what credentials are checked (org-wide token, SSO) and under what conditions they are active (when configured, hub_url set, or after sso_login). This goes beyond the structured annotations without contradicting them.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is two sentences, front-loaded with the core purpose ('Reports which credentials are active'), followed by specific conditions. Every sentence is information-dense with no filler.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple zero-parameter status tool with no output schema, the description provides sufficient context: what it reports, the credential types and conditions, and when to use it. It doesn't leave the agent guessing about its role in the toolset.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The tool has zero parameters, so schema coverage is trivially 100%. The baseline for no parameters is 4, and the description appropriately includes no parameter details since none exist.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description uses the specific verb 'Reports' and identifies the resource as 'which credentials are active in this MCP session'. It clearly distinguishes from sibling tools like audit_search or configure_tenant, which serve different purposes.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
It explicitly states when to call: 'Call before choosing org-token admin tools vs my_* / SSO self-service tools.' This gives the agent a direct usage directive and clarifies the decision it helps make.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Returns the complete catalog of AdvocateHub MCP tools with names and descriptions. Use this to discover, search, find, or list every available tool when tool_search only shows a subset. Filter by keyword (e.g. "member", "search", "reward", "challenge") or credential scope. No tenant credentials required.
| Name | Required | Description | Default |
|---|---|---|---|
| query | No | Optional filter — case-insensitive substring match against tool name, title, or description. | |
| credential | No | Filter by credential scope: org_token (integration API), sso (signed-in user), or any. | any |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Annotations already declare readOnlyHint=true and destructiveHint=false, and the description adds useful context: 'No tenant credentials required' and filtering capabilities. It doesn't contradict annotations and provides extra behavioral insight beyond the safety flags.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Two sentences, front-loaded with the main purpose, and packed with actionable details. The examples are relevant without unnecessary verbosity; every sentence contributes value.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
For a simple list tool with no output schema, the description covers return content, filtering options, and credential requirements. It's self-contained and complete; no missing aspects that an agent would need to know.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
The schema already describes both parameters fully (100% coverage). The description adds value with example keywords ('member', 'search', 'reward', 'challenge') and explains the credential scope enum more concretely, going beyond the schema definitions.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states 'Returns the complete catalog of AdvocateHub MCP tools with names and descriptions' with a specific verb and resource. It distinguishes itself from tool_search by noting it shows every tool when tool_search only shows a subset.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Explicitly says 'Use this to discover, search, find, or list every available tool when tool_search only shows a subset', giving a clear use case. It also provides filtering guidance with examples and the no-credentials requirement, which helps the agent decide when to invoke it.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections. Dates show when Glama detected each change.
v0.1.0audit_searchaudit_tailconfigure_tenantget_active_identity_contextlist_advocatehub_toolsThe tools are mostly distinct: list_advocatehub_tools for discovery, configure_tenant for setup, get_active_identity_context for session context. The only potential confusion is between audit_tail and audit_search, but they are differentiated by recency vs. filtered search, and the descriptions clarify the distinction.
All tool names use snake_case and are readable. Most follow a verb_first pattern (list_, configure_, get_), but audit_tail and audit_search place the resource (audit) before the verb, a minor deviation from the otherwise consistent convention.
With five tools, the count falls within the typical 3-15 range and feels reasonable for a utility/admin-focused server. It is slightly on the smaller side given the apparent domain, but not inappropriately sparse.
The server name and list_advocatehub_tools description reference domain objects like members, rewards, and challenges, yet none of the actual tools perform any domain operations. The set is limited to configuration, identity, and audit utilities, leaving the core AdvocateHub functionality completely absent. Even within the meta-purpose, there is no way to modify configuration or manage audit logs beyond reading them.
Unclaimed servers have limited discoverability.
If you are the server author, to access and configure the admin panel.
Unified MCP Server is a remote MCP connector for AI agents and vertical AI products that provides access to 22,000+ authorized SaaS tools across 400+ integrations and 24 categories directly inside LLMs (Claude, GPT, Gemini, Cohere). Tools operate only on explicitly authorized customer connections, enabling agents to safely read and write against live third-party systems.
63 MCP tools for loyalty programs, rewards, and member operations with HITL approval.
The HubSpot MCP Server acts as a bridge that enables AI assistants and Large Language Models to securely interact with HubSpot CRM data through natural conversation, without requiring users to understand complex API structures. It provides read-only access to standard CRM objects (contacts, companies, deals, tickets, products, invoices, and more) and their associations, secured via OAuth 2.0, allowing AI agents to perform tasks like summarizing deals, fetching company updates, and looking up record changes.
Authenticated MCP server for ClearPolicy policy and compliance workflows.
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/akashtrilogy/advocatehub-influitive-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server
